< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6387 in Layer 44

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 8.3040. Min Range: -8.3040

Max Act: 8.2415. Min Act: -0.1700

Data Index: 7697808 (Open Web Text)

Max Activating Token Index: 130

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 8.3040. Min Range: -8.3040

Max Act: 8.3040. Min Act: -0.1700

Data Index: 1673024 (Open Web Text)

Max Activating Token Index: 297

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 8.3040. Min Range: -8.3040

Max Act: 8.0853. Min Act: -0.1700

Data Index: 5555419 (Open Web Text)

Max Activating Token Index: 131

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 8.3040. Min Range: -8.3040

Max Act: 8.0853. Min Act: -0.1700

Data Index: 2458548 (Open Web Text)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 8.3040. Min Range: -8.3040

Max Act: 8.0853. Min Act: -0.1700

Data Index: 2870166 (Open Web Text)

Max Activating Token Index: 1016

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 8.3040. Min Range: -8.3040

Max Act: 8.0853. Min Act: -0.1700

Data Index: 7948491 (Open Web Text)

Max Activating Token Index: 696

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 8.3040. Min Range: -8.3040

Max Act: 8.0540. Min Act: -0.1700

Data Index: 4541792 (Open Web Text)

Max Activating Token Index: 820

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 8.3040. Min Range: -8.3040

Max Act: 7.9915. Min Act: -0.1700

Data Index: 3581599 (Open Web Text)

Max Activating Token Index: 144

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 8.3040. Min Range: -8.3040

Max Act: 7.9603. Min Act: -0.1700

Data Index: 1735579 (Open Web Text)

Max Activating Token Index: 698

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 8.3040. Min Range: -8.3040

Max Act: 7.9290. Min Act: -0.1700

Data Index: 3010888 (Open Web Text)

Max Activating Token Index: 492

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 8.3040. Min Range: -8.3040

Max Act: 7.9290. Min Act: -0.1700

Data Index: 4723592 (Open Web Text)

Max Activating Token Index: 672

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 8.3040. Min Range: -8.3040

Max Act: 7.8353. Min Act: -0.1700

Data Index: 7229607 (Open Web Text)

Max Activating Token Index: 767

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 8.3040. Min Range: -8.3040

Max Act: 7.8353. Min Act: -0.1700

Data Index: 1402374 (Open Web Text)

Max Activating Token Index: 822

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 8.3040. Min Range: -8.3040

Max Act: 7.8040. Min Act: -0.1700

Data Index: 7059284 (Open Web Text)

Max Activating Token Index: 476

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 8.3040. Min Range: -8.3040

Max Act: 7.8040. Min Act: -0.1700

Data Index: 5700920 (Open Web Text)

Max Activating Token Index: 886

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 8.3040. Min Range: -8.3040

Max Act: 7.7728. Min Act: -0.1700

Data Index: 160525 (Open Web Text)

Max Activating Token Index: 456

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 8.3040. Min Range: -8.3040

Max Act: 7.7415. Min Act: -0.1700

Data Index: 7062626 (Open Web Text)

Max Activating Token Index: 605

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 8.3040. Min Range: -8.3040

Max Act: 7.7728. Min Act: -0.1700

Data Index: 2227699 (Open Web Text)

Max Activating Token Index: 952

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 8.3040. Min Range: -8.3040

Max Act: 7.8040. Min Act: -0.1700

Data Index: 4492116 (Open Web Text)

Max Activating Token Index: 207

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 8.3040. Min Range: -8.3040

Max Act: 7.7728. Min Act: -0.1700

Data Index: 2299308 (Open Web Text)

Max Activating Token Index: 98

Click toggle to see full text

Truncated

Full Text #19