Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1801 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8995. Min Range: -3.8995
Max Act: 3.8995. Min Act: -0.1700
Data Index: 3576374 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8995. Min Range: -3.8995
Max Act: 3.8057. Min Act: -0.1700
Data Index: 3096926 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8995. Min Range: -3.8995
Max Act: 3.8370. Min Act: -0.1700
Data Index: 8801435 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8995. Min Range: -3.8995
Max Act: 3.8057. Min Act: -0.1700
Data Index: 6809224 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8995. Min Range: -3.8995
Max Act: 3.7744. Min Act: -0.1700
Data Index: 7300315 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8995. Min Range: -3.8995
Max Act: 3.7431. Min Act: -0.1700
Data Index: 2147094 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8995. Min Range: -3.8995
Max Act: 3.7431. Min Act: -0.1700
Data Index: 1479709 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8995. Min Range: -3.8995
Max Act: 3.7119. Min Act: -0.1700
Data Index: 7486007 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8995. Min Range: -3.8995
Max Act: 3.7119. Min Act: -0.1700
Data Index: 5065098 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8995. Min Range: -3.8995
Max Act: 3.6806. Min Act: -0.1700
Data Index: 3536547 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8995. Min Range: -3.8995
Max Act: 3.7119. Min Act: -0.1700
Data Index: 5760587 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8995. Min Range: -3.8995
Max Act: 3.6806. Min Act: -0.1700
Data Index: 1790003 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8995. Min Range: -3.8995
Max Act: 3.6806. Min Act: -0.1700
Data Index: 5515054 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8995. Min Range: -3.8995
Max Act: 3.7119. Min Act: -0.1700
Data Index: 3722280 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8995. Min Range: -3.8995
Max Act: 3.6806. Min Act: -0.1700
Data Index: 2043530 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8995. Min Range: -3.8995
Max Act: 3.6806. Min Act: -0.1700
Data Index: 215857 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8995. Min Range: -3.8995
Max Act: 3.6493. Min Act: -0.1700
Data Index: 7669198 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8995. Min Range: -3.8995
Max Act: 3.7119. Min Act: -0.1700
Data Index: 2372273 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8995. Min Range: -3.8995
Max Act: 3.6806. Min Act: -0.1700
Data Index: 5998440 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8995. Min Range: -3.8995
Max Act: 3.6806. Min Act: -0.1700
Data Index: 5587403 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19