< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 6350 in Layer 37

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')



Text #0

Max Range: 10.2210. Min Range: -10.2210

Max Act: 10.2210. Min Act: -0.1700

Data Index: 7920206 (Open Web Text)

Max Activating Token Index: 111

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.2210. Min Range: -10.2210

Max Act: 9.7210. Min Act: -0.1700

Data Index: 2133710 (Open Web Text)

Max Activating Token Index: 417

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.2210. Min Range: -10.2210

Max Act: 9.5960. Min Act: -0.1700

Data Index: 6553094 (Open Web Text)

Max Activating Token Index: 439

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.2210. Min Range: -10.2210

Max Act: 9.5960. Min Act: -0.1700

Data Index: 4400552 (Open Web Text)

Max Activating Token Index: 793

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.2210. Min Range: -10.2210

Max Act: 9.5960. Min Act: -0.1700

Data Index: 5772380 (Open Web Text)

Max Activating Token Index: 1017

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.2210. Min Range: -10.2210

Max Act: 9.5335. Min Act: -0.1700

Data Index: 1995827 (Open Web Text)

Max Activating Token Index: 969

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.2210. Min Range: -10.2210

Max Act: 9.5960. Min Act: -0.1700

Data Index: 7191449 (Open Web Text)

Max Activating Token Index: 561

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.2210. Min Range: -10.2210

Max Act: 9.5335. Min Act: -0.1700

Data Index: 4571895 (Open Web Text)

Max Activating Token Index: 724

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.2210. Min Range: -10.2210

Max Act: 9.5335. Min Act: -0.1700

Data Index: 8051347 (Open Web Text)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.2210. Min Range: -10.2210

Max Act: 9.4710. Min Act: -0.1700

Data Index: 1249171 (Open Web Text)

Max Activating Token Index: 397

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.2210. Min Range: -10.2210

Max Act: 9.4710. Min Act: -0.1700

Data Index: 4115630 (Open Web Text)

Max Activating Token Index: 688

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.2210. Min Range: -10.2210

Max Act: 9.4085. Min Act: -0.1700

Data Index: 6239244 (Open Web Text)

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.2210. Min Range: -10.2210

Max Act: 9.4085. Min Act: -0.1700

Data Index: 747430 (Open Web Text)

Max Activating Token Index: 203

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.2210. Min Range: -10.2210

Max Act: 9.4085. Min Act: -0.1700

Data Index: 1494377 (Open Web Text)

Max Activating Token Index: 840

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.2210. Min Range: -10.2210

Max Act: 9.3460. Min Act: -0.1700

Data Index: 4204612 (Open Web Text)

Max Activating Token Index: 369

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.2210. Min Range: -10.2210

Max Act: 9.3460. Min Act: -0.1700

Data Index: 2540613 (Open Web Text)

Max Activating Token Index: 239

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.2210. Min Range: -10.2210

Max Act: 9.3460. Min Act: -0.1700

Data Index: 2192265 (Open Web Text)

Max Activating Token Index: 404

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.2210. Min Range: -10.2210

Max Act: 9.3460. Min Act: -0.1700

Data Index: 179513 (Open Web Text)

Max Activating Token Index: 835

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.2210. Min Range: -10.2210

Max Act: 9.2835. Min Act: -0.1700

Data Index: 5827404 (Open Web Text)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.2210. Min Range: -10.2210

Max Act: 9.2835. Min Act: -0.1700

Data Index: 6227663 (Open Web Text)

Max Activating Token Index: 146

Click toggle to see full text

Truncated

Full Text #19