Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2156 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4355. Min Range: -6.4355
Max Act: 6.4355. Min Act: -0.1700
Data Index: 5417303 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4355. Min Range: -6.4355
Max Act: 6.2793. Min Act: -0.1700
Data Index: 5027713 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4355. Min Range: -6.4355
Max Act: 6.2480. Min Act: -0.1700
Data Index: 4492368 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4355. Min Range: -6.4355
Max Act: 6.2168. Min Act: -0.1700
Data Index: 4338318 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4355. Min Range: -6.4355
Max Act: 6.1855. Min Act: -0.1700
Data Index: 5734059 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4355. Min Range: -6.4355
Max Act: 6.2168. Min Act: -0.1700
Data Index: 1064165 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4355. Min Range: -6.4355
Max Act: 6.1543. Min Act: -0.1700
Data Index: 1507792 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4355. Min Range: -6.4355
Max Act: 6.1543. Min Act: -0.1700
Data Index: 1064166 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4355. Min Range: -6.4355
Max Act: 6.1543. Min Act: -0.1700
Data Index: 3483114 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4355. Min Range: -6.4355
Max Act: 6.1543. Min Act: -0.1700
Data Index: 3011897 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4355. Min Range: -6.4355
Max Act: 6.1543. Min Act: -0.1700
Data Index: 2798005 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4355. Min Range: -6.4355
Max Act: 6.1230. Min Act: -0.1700
Data Index: 4492367 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4355. Min Range: -6.4355
Max Act: 6.1230. Min Act: -0.1700
Data Index: 1295254 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4355. Min Range: -6.4355
Max Act: 6.0918. Min Act: -0.1700
Data Index: 1583941 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4355. Min Range: -6.4355
Max Act: 6.1230. Min Act: -0.1700
Data Index: 2076269 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4355. Min Range: -6.4355
Max Act: 6.1230. Min Act: -0.1700
Data Index: 639129 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4355. Min Range: -6.4355
Max Act: 6.0918. Min Act: -0.1700
Data Index: 4205380 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4355. Min Range: -6.4355
Max Act: 6.0918. Min Act: -0.1700
Data Index: 3710510 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4355. Min Range: -6.4355
Max Act: 6.0605. Min Act: -0.1700
Data Index: 956700 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4355. Min Range: -6.4355
Max Act: 6.0918. Min Act: -0.1700
Data Index: 3011898 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19