Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3312 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4661. Min Range: -4.4661
Max Act: 4.4661. Min Act: -0.1700
Data Index: 4306152 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4661. Min Range: -4.4661
Max Act: 4.4661. Min Act: -0.1700
Data Index: 4021946 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4661. Min Range: -4.4661
Max Act: 4.4036. Min Act: -0.1700
Data Index: 6413574 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4661. Min Range: -4.4661
Max Act: 4.4036. Min Act: -0.1700
Data Index: 6550432 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4661. Min Range: -4.4661
Max Act: 4.3724. Min Act: -0.1700
Data Index: 5584552 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4661. Min Range: -4.4661
Max Act: 4.3724. Min Act: -0.1700
Data Index: 6426364 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4661. Min Range: -4.4661
Max Act: 4.3724. Min Act: -0.1700
Data Index: 4387247 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4661. Min Range: -4.4661
Max Act: 4.3724. Min Act: -0.1700
Data Index: 6623021 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4661. Min Range: -4.4661
Max Act: 4.3099. Min Act: -0.1700
Data Index: 3676962 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4661. Min Range: -4.4661
Max Act: 4.3411. Min Act: -0.1700
Data Index: 2685622 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4661. Min Range: -4.4661
Max Act: 4.3411. Min Act: -0.1700
Data Index: 1880028 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4661. Min Range: -4.4661
Max Act: 4.3411. Min Act: -0.1700
Data Index: 8310157 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4661. Min Range: -4.4661
Max Act: 4.3411. Min Act: -0.1700
Data Index: 1916685 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4661. Min Range: -4.4661
Max Act: 4.3411. Min Act: -0.1700
Data Index: 758550 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4661. Min Range: -4.4661
Max Act: 4.3099. Min Act: -0.1700
Data Index: 2559882 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4661. Min Range: -4.4661
Max Act: 4.3099. Min Act: -0.1700
Data Index: 7402507 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4661. Min Range: -4.4661
Max Act: 4.3099. Min Act: -0.1700
Data Index: 3379002 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4661. Min Range: -4.4661
Max Act: 4.3099. Min Act: -0.1700
Data Index: 1860742 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4661. Min Range: -4.4661
Max Act: 4.3099. Min Act: -0.1700
Data Index: 6048461 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4661. Min Range: -4.4661
Max Act: 4.3099. Min Act: -0.1700
Data Index: 1721880 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19