Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5128 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.9825. Min Act: -0.1700
Data Index: 8196344 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.7950. Min Act: -0.1700
Data Index: 2895404 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.6700. Min Act: -0.1700
Data Index: 1250834 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.6075. Min Act: -0.1700
Data Index: 4484885 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.5450. Min Act: -0.1700
Data Index: 8694571 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.5137. Min Act: -0.1700
Data Index: 5103790 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.5137. Min Act: -0.1700
Data Index: 88147 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.5137. Min Act: -0.1700
Data Index: 6827925 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.4825. Min Act: -0.1700
Data Index: 6868272 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.4200. Min Act: -0.1700
Data Index: 467811 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.3887. Min Act: -0.1700
Data Index: 113438 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.4200. Min Act: -0.1700
Data Index: 818338 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.4200. Min Act: -0.1700
Data Index: 7292796 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.3887. Min Act: -0.1700
Data Index: 4623489 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.3262. Min Act: -0.1700
Data Index: 7323785 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.2637. Min Act: -0.1700
Data Index: 3363887 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.2950. Min Act: -0.1700
Data Index: 3180460 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.2637. Min Act: -0.1700
Data Index: 4658360 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.2637. Min Act: -0.1700
Data Index: 48697 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.2325. Min Act: -0.1700
Data Index: 362242 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19