Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4382 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1865. Min Range: -5.1865
Max Act: 5.1865. Min Act: -0.1700
Data Index: 4341511 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1865. Min Range: -5.1865
Max Act: 5.0615. Min Act: -0.1700
Data Index: 1387280 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1865. Min Range: -5.1865
Max Act: 4.8740. Min Act: -0.1700
Data Index: 850303 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1865. Min Range: -5.1865
Max Act: 4.8428. Min Act: -0.1700
Data Index: 2157367 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1865. Min Range: -5.1865
Max Act: 4.8115. Min Act: -0.1700
Data Index: 8305046 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1865. Min Range: -5.1865
Max Act: 4.8428. Min Act: -0.1700
Data Index: 208931 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1865. Min Range: -5.1865
Max Act: 4.7803. Min Act: -0.1700
Data Index: 8065886 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1865. Min Range: -5.1865
Max Act: 4.7803. Min Act: -0.1700
Data Index: 8107232 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1865. Min Range: -5.1865
Max Act: 4.7490. Min Act: -0.1700
Data Index: 7258805 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1865. Min Range: -5.1865
Max Act: 4.7490. Min Act: -0.1700
Data Index: 2892500 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1865. Min Range: -5.1865
Max Act: 4.7490. Min Act: -0.1700
Data Index: 1469679 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1865. Min Range: -5.1865
Max Act: 4.7490. Min Act: -0.1700
Data Index: 1513346 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1865. Min Range: -5.1865
Max Act: 4.7178. Min Act: -0.1700
Data Index: 673318 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1865. Min Range: -5.1865
Max Act: 4.7178. Min Act: -0.1700
Data Index: 1134277 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1865. Min Range: -5.1865
Max Act: 4.7178. Min Act: -0.1700
Data Index: 1590028 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1865. Min Range: -5.1865
Max Act: 4.6865. Min Act: -0.1700
Data Index: 7268853 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1865. Min Range: -5.1865
Max Act: 4.6865. Min Act: -0.1700
Data Index: 8494997 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1865. Min Range: -5.1865
Max Act: 4.6865. Min Act: -0.1700
Data Index: 4260981 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1865. Min Range: -5.1865
Max Act: 4.6865. Min Act: -0.1700
Data Index: 2105998 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1865. Min Range: -5.1865
Max Act: 4.6240. Min Act: -0.1700
Data Index: 2539966 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19