< Prev | Home | Model | Random | Next >

Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 883 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')



Text #0

Max Range: 2.8283. Min Range: -2.8283

Max Act: 2.8283. Min Act: -0.1700

Data Index: 569688 (C4 (Web Text))

Max Activating Token Index: 104

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.8283. Min Range: -2.8283

Max Act: 2.6687. Min Act: -0.1700

Data Index: 1353738 (C4 (Web Text))

Max Activating Token Index: 449

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.8283. Min Range: -2.8283

Max Act: 2.6366. Min Act: -0.1700

Data Index: 253545 (C4 (Web Text))

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.8283. Min Range: -2.8283

Max Act: 2.6366. Min Act: -0.1700

Data Index: 473015 (C4 (Web Text))

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.8283. Min Range: -2.8283

Max Act: 2.6044. Min Act: -0.1700

Data Index: 951527 (C4 (Web Text))

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.8283. Min Range: -2.8283

Max Act: 2.6044. Min Act: -0.1700

Data Index: 195693 (C4 (Web Text))

Max Activating Token Index: 926

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.8283. Min Range: -2.8283

Max Act: 2.6044. Min Act: -0.1700

Data Index: 220 (C4 (Web Text))

Max Activating Token Index: 955

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.8283. Min Range: -2.8283

Max Act: 2.5561. Min Act: -0.1700

Data Index: 1340213 (C4 (Web Text))

Max Activating Token Index: 747

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.8283. Min Range: -2.8283

Max Act: 2.5722. Min Act: -0.1700

Data Index: 213415 (C4 (Web Text))

Max Activating Token Index: 850

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.8283. Min Range: -2.8283

Max Act: 2.5561. Min Act: -0.1700

Data Index: 37511 (C4 (Web Text))

Max Activating Token Index: 215

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.8283. Min Range: -2.8283

Max Act: 2.5400. Min Act: -0.1700

Data Index: 1553143 (Python Code)

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.8283. Min Range: -2.8283

Max Act: 2.5561. Min Act: -0.1700

Data Index: 1648986 (Python Code)

Max Activating Token Index: 767

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.8283. Min Range: -2.8283

Max Act: 2.5400. Min Act: -0.1700

Data Index: 1341903 (C4 (Web Text))

Max Activating Token Index: 890

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.8283. Min Range: -2.8283

Max Act: 2.5561. Min Act: -0.1700

Data Index: 964655 (C4 (Web Text))

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.8283. Min Range: -2.8283

Max Act: 2.5400. Min Act: -0.1700

Data Index: 288664 (C4 (Web Text))

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.8283. Min Range: -2.8283

Max Act: 2.5561. Min Act: -0.1700

Data Index: 751428 (C4 (Web Text))

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.8283. Min Range: -2.8283

Max Act: 2.5400. Min Act: -0.1700

Data Index: 897704 (C4 (Web Text))

Max Activating Token Index: 280

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.8283. Min Range: -2.8283

Max Act: 2.5238. Min Act: -0.1700

Data Index: 186253 (C4 (Web Text))

Max Activating Token Index: 148

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.8283. Min Range: -2.8283

Max Act: 2.5238. Min Act: -0.1700

Data Index: 675978 (C4 (Web Text))

Max Activating Token Index: 115

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.8283. Min Range: -2.8283

Max Act: 2.5238. Min Act: -0.1700

Data Index: 1274496 (C4 (Web Text))

Max Activating Token Index: 288

Click toggle to see full text

Truncated

Full Text #19