Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 981 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9268. Min Range: -8.9268
Max Act: 8.9268. Min Act: -0.1700
Data Index: 5401495 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9268. Min Range: -8.9268
Max Act: 8.5518. Min Act: -0.1700
Data Index: 5906802 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9268. Min Range: -8.9268
Max Act: 8.5518. Min Act: -0.1700
Data Index: 2974515 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9268. Min Range: -8.9268
Max Act: 8.4893. Min Act: -0.1700
Data Index: 7698381 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9268. Min Range: -8.9268
Max Act: 8.4268. Min Act: -0.1700
Data Index: 4026997 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9268. Min Range: -8.9268
Max Act: 8.4268. Min Act: -0.1700
Data Index: 4934583 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9268. Min Range: -8.9268
Max Act: 8.3018. Min Act: -0.1700
Data Index: 8230630 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9268. Min Range: -8.9268
Max Act: 8.1768. Min Act: -0.1700
Data Index: 3337532 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9268. Min Range: -8.9268
Max Act: 8.1768. Min Act: -0.1700
Data Index: 8250865 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9268. Min Range: -8.9268
Max Act: 8.1143. Min Act: -0.1700
Data Index: 7801578 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9268. Min Range: -8.9268
Max Act: 8.1143. Min Act: -0.1700
Data Index: 2541724 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9268. Min Range: -8.9268
Max Act: 8.0518. Min Act: -0.1700
Data Index: 3597345 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9268. Min Range: -8.9268
Max Act: 8.0518. Min Act: -0.1700
Data Index: 4002149 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9268. Min Range: -8.9268
Max Act: 8.1143. Min Act: -0.1700
Data Index: 5117210 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9268. Min Range: -8.9268
Max Act: 8.0518. Min Act: -0.1700
Data Index: 5318218 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9268. Min Range: -8.9268
Max Act: 8.0518. Min Act: -0.1700
Data Index: 35923 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9268. Min Range: -8.9268
Max Act: 8.0518. Min Act: -0.1700
Data Index: 753984 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9268. Min Range: -8.9268
Max Act: 8.0518. Min Act: -0.1700
Data Index: 8674341 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9268. Min Range: -8.9268
Max Act: 7.9893. Min Act: -0.1700
Data Index: 3572117 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9268. Min Range: -8.9268
Max Act: 7.9893. Min Act: -0.1700
Data Index: 1100068 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19