Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2834 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4098. Min Range: -4.4098
Max Act: 4.4098. Min Act: -0.1700
Data Index: 5032276 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4098. Min Range: -4.4098
Max Act: 4.4098. Min Act: -0.1700
Data Index: 6789770 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4098. Min Range: -4.4098
Max Act: 4.3785. Min Act: -0.1700
Data Index: 2267876 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4098. Min Range: -4.4098
Max Act: 4.3785. Min Act: -0.1700
Data Index: 6109166 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4098. Min Range: -4.4098
Max Act: 4.2848. Min Act: -0.1700
Data Index: 8262988 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4098. Min Range: -4.4098
Max Act: 4.3160. Min Act: -0.1700
Data Index: 1731910 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4098. Min Range: -4.4098
Max Act: 4.3473. Min Act: -0.1700
Data Index: 6176930 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4098. Min Range: -4.4098
Max Act: 4.3160. Min Act: -0.1700
Data Index: 3383453 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4098. Min Range: -4.4098
Max Act: 4.2535. Min Act: -0.1700
Data Index: 317279 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4098. Min Range: -4.4098
Max Act: 4.2848. Min Act: -0.1700
Data Index: 3151155 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4098. Min Range: -4.4098
Max Act: 4.2535. Min Act: -0.1700
Data Index: 1875588 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4098. Min Range: -4.4098
Max Act: 4.2535. Min Act: -0.1700
Data Index: 679762 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4098. Min Range: -4.4098
Max Act: 4.2535. Min Act: -0.1700
Data Index: 4777467 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4098. Min Range: -4.4098
Max Act: 4.2535. Min Act: -0.1700
Data Index: 8597497 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4098. Min Range: -4.4098
Max Act: 4.2535. Min Act: -0.1700
Data Index: 7969947 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4098. Min Range: -4.4098
Max Act: 4.2223. Min Act: -0.1700
Data Index: 4379495 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4098. Min Range: -4.4098
Max Act: 4.2223. Min Act: -0.1700
Data Index: 3279823 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4098. Min Range: -4.4098
Max Act: 4.1910. Min Act: -0.1700
Data Index: 5890893 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4098. Min Range: -4.4098
Max Act: 4.1910. Min Act: -0.1700
Data Index: 6218230 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4098. Min Range: -4.4098
Max Act: 4.2223. Min Act: -0.1700
Data Index: 1150076 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19