Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4161 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7055. Min Range: -9.7055
Max Act: 9.7055. Min Act: -0.1700
Data Index: 748885 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7055. Min Range: -9.7055
Max Act: 9.2680. Min Act: -0.1700
Data Index: 2775491 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7055. Min Range: -9.7055
Max Act: 9.0180. Min Act: -0.1700
Data Index: 8800537 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7055. Min Range: -9.7055
Max Act: 9.0180. Min Act: -0.1700
Data Index: 5908607 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7055. Min Range: -9.7055
Max Act: 8.9555. Min Act: -0.1700
Data Index: 1580756 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7055. Min Range: -9.7055
Max Act: 8.8930. Min Act: -0.1700
Data Index: 3642977 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7055. Min Range: -9.7055
Max Act: 8.8305. Min Act: -0.1700
Data Index: 2968725 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7055. Min Range: -9.7055
Max Act: 8.7680. Min Act: -0.1700
Data Index: 6880485 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7055. Min Range: -9.7055
Max Act: 8.6430. Min Act: -0.1700
Data Index: 2228499 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7055. Min Range: -9.7055
Max Act: 8.7055. Min Act: -0.1700
Data Index: 4543410 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7055. Min Range: -9.7055
Max Act: 8.7055. Min Act: -0.1700
Data Index: 5197982 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7055. Min Range: -9.7055
Max Act: 8.7055. Min Act: -0.1700
Data Index: 5855798 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7055. Min Range: -9.7055
Max Act: 8.6430. Min Act: -0.1700
Data Index: 3388246 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7055. Min Range: -9.7055
Max Act: 8.6430. Min Act: -0.1700
Data Index: 544772 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7055. Min Range: -9.7055
Max Act: 8.6430. Min Act: -0.1700
Data Index: 6718920 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7055. Min Range: -9.7055
Max Act: 8.5805. Min Act: -0.1700
Data Index: 7218626 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7055. Min Range: -9.7055
Max Act: 8.6430. Min Act: -0.1700
Data Index: 5330054 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7055. Min Range: -9.7055
Max Act: 8.5805. Min Act: -0.1700
Data Index: 7074504 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7055. Min Range: -9.7055
Max Act: 8.5805. Min Act: -0.1700
Data Index: 3125364 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7055. Min Range: -9.7055
Max Act: 8.5805. Min Act: -0.1700
Data Index: 6070860 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19