Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 358 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4288. Min Range: -7.4288
Max Act: 7.4288. Min Act: -0.1700
Data Index: 4046794 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4288. Min Range: -7.4288
Max Act: 7.2413. Min Act: -0.1700
Data Index: 3028000 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4288. Min Range: -7.4288
Max Act: 7.1163. Min Act: -0.1700
Data Index: 3130106 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4288. Min Range: -7.4288
Max Act: 7.0226. Min Act: -0.1700
Data Index: 7012818 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4288. Min Range: -7.4288
Max Act: 7.0226. Min Act: -0.1700
Data Index: 4591472 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4288. Min Range: -7.4288
Max Act: 6.9913. Min Act: -0.1700
Data Index: 4115865 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4288. Min Range: -7.4288
Max Act: 6.9913. Min Act: -0.1700
Data Index: 2473003 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4288. Min Range: -7.4288
Max Act: 6.9288. Min Act: -0.1700
Data Index: 2979972 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4288. Min Range: -7.4288
Max Act: 6.9288. Min Act: -0.1700
Data Index: 2677816 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4288. Min Range: -7.4288
Max Act: 6.8663. Min Act: -0.1700
Data Index: 7735192 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4288. Min Range: -7.4288
Max Act: 6.8663. Min Act: -0.1700
Data Index: 2042369 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4288. Min Range: -7.4288
Max Act: 6.8351. Min Act: -0.1700
Data Index: 2827675 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4288. Min Range: -7.4288
Max Act: 6.8038. Min Act: -0.1700
Data Index: 6985792 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4288. Min Range: -7.4288
Max Act: 6.8351. Min Act: -0.1700
Data Index: 327147 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4288. Min Range: -7.4288
Max Act: 6.8351. Min Act: -0.1700
Data Index: 1884984 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4288. Min Range: -7.4288
Max Act: 6.8038. Min Act: -0.1700
Data Index: 650092 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4288. Min Range: -7.4288
Max Act: 6.8038. Min Act: -0.1700
Data Index: 1112085 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4288. Min Range: -7.4288
Max Act: 6.7413. Min Act: -0.1700
Data Index: 382278 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4288. Min Range: -7.4288
Max Act: 6.7413. Min Act: -0.1700
Data Index: 7031842 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4288. Min Range: -7.4288
Max Act: 6.7413. Min Act: -0.1700
Data Index: 5074852 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19