Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1529 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9429. Min Range: -6.9429
Max Act: 6.9429. Min Act: -0.1700
Data Index: 7450651 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9429. Min Range: -6.9429
Max Act: 6.8491. Min Act: -0.1700
Data Index: 6753636 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9429. Min Range: -6.9429
Max Act: 6.6304. Min Act: -0.1700
Data Index: 7186029 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9429. Min Range: -6.9429
Max Act: 6.5366. Min Act: -0.1700
Data Index: 3162908 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9429. Min Range: -6.9429
Max Act: 6.4116. Min Act: -0.1700
Data Index: 771794 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9429. Min Range: -6.9429
Max Act: 6.3804. Min Act: -0.1700
Data Index: 3048418 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9429. Min Range: -6.9429
Max Act: 6.3804. Min Act: -0.1700
Data Index: 5724502 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9429. Min Range: -6.9429
Max Act: 6.3804. Min Act: -0.1700
Data Index: 8150242 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9429. Min Range: -6.9429
Max Act: 6.3804. Min Act: -0.1700
Data Index: 2509119 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9429. Min Range: -6.9429
Max Act: 6.3491. Min Act: -0.1700
Data Index: 7080361 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9429. Min Range: -6.9429
Max Act: 6.3179. Min Act: -0.1700
Data Index: 2904572 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9429. Min Range: -6.9429
Max Act: 6.2554. Min Act: -0.1700
Data Index: 1292332 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9429. Min Range: -6.9429
Max Act: 6.2866. Min Act: -0.1700
Data Index: 6084798 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9429. Min Range: -6.9429
Max Act: 6.2866. Min Act: -0.1700
Data Index: 7675844 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9429. Min Range: -6.9429
Max Act: 6.2866. Min Act: -0.1700
Data Index: 5027098 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9429. Min Range: -6.9429
Max Act: 6.3179. Min Act: -0.1700
Data Index: 2302125 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9429. Min Range: -6.9429
Max Act: 6.2554. Min Act: -0.1700
Data Index: 2825819 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9429. Min Range: -6.9429
Max Act: 6.2866. Min Act: -0.1700
Data Index: 839489 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9429. Min Range: -6.9429
Max Act: 6.2241. Min Act: -0.1700
Data Index: 3177923 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9429. Min Range: -6.9429
Max Act: 6.2241. Min Act: -0.1700
Data Index: 3429367 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19