Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3157 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.7772. Min Range: -12.7772
Max Act: 12.7772. Min Act: -0.1700
Data Index: 6039396 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.7772. Min Range: -12.7772
Max Act: 12.3397. Min Act: -0.1700
Data Index: 4061625 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.7772. Min Range: -12.7772
Max Act: 12.2772. Min Act: -0.1700
Data Index: 5894925 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.7772. Min Range: -12.7772
Max Act: 12.2772. Min Act: -0.1700
Data Index: 4073244 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.7772. Min Range: -12.7772
Max Act: 12.2147. Min Act: -0.1700
Data Index: 1919336 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.7772. Min Range: -12.7772
Max Act: 12.2147. Min Act: -0.1700
Data Index: 2774259 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.7772. Min Range: -12.7772
Max Act: 12.2147. Min Act: -0.1700
Data Index: 6764888 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.7772. Min Range: -12.7772
Max Act: 12.0272. Min Act: -0.1700
Data Index: 3744766 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.7772. Min Range: -12.7772
Max Act: 12.0897. Min Act: -0.1700
Data Index: 8270092 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.7772. Min Range: -12.7772
Max Act: 12.0897. Min Act: -0.1700
Data Index: 7140235 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.7772. Min Range: -12.7772
Max Act: 12.0897. Min Act: -0.1700
Data Index: 8150799 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.7772. Min Range: -12.7772
Max Act: 12.0272. Min Act: -0.1700
Data Index: 270262 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.7772. Min Range: -12.7772
Max Act: 12.0272. Min Act: -0.1700
Data Index: 3760344 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.7772. Min Range: -12.7772
Max Act: 12.0272. Min Act: -0.1700
Data Index: 3312788 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.7772. Min Range: -12.7772
Max Act: 11.9647. Min Act: -0.1700
Data Index: 6173111 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.7772. Min Range: -12.7772
Max Act: 11.9647. Min Act: -0.1700
Data Index: 3166731 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.7772. Min Range: -12.7772
Max Act: 11.9647. Min Act: -0.1700
Data Index: 5556765 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.7772. Min Range: -12.7772
Max Act: 11.9647. Min Act: -0.1700
Data Index: 698083 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.7772. Min Range: -12.7772
Max Act: 11.9022. Min Act: -0.1700
Data Index: 2600066 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.7772. Min Range: -12.7772
Max Act: 11.8397. Min Act: -0.1700
Data Index: 5107699 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19