Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4186 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2978. Min Range: -10.2978
Max Act: 10.2978. Min Act: -0.1700
Data Index: 4788192 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2978. Min Range: -10.2978
Max Act: 9.6728. Min Act: -0.1700
Data Index: 6039393 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2978. Min Range: -10.2978
Max Act: 9.6103. Min Act: -0.1700
Data Index: 6694795 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2978. Min Range: -10.2978
Max Act: 9.6103. Min Act: -0.1700
Data Index: 7414248 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2978. Min Range: -10.2978
Max Act: 9.5478. Min Act: -0.1700
Data Index: 4348 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2978. Min Range: -10.2978
Max Act: 9.4853. Min Act: -0.1700
Data Index: 2587220 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2978. Min Range: -10.2978
Max Act: 9.4853. Min Act: -0.1700
Data Index: 8235121 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2978. Min Range: -10.2978
Max Act: 9.4853. Min Act: -0.1700
Data Index: 5361918 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2978. Min Range: -10.2978
Max Act: 9.4853. Min Act: -0.1700
Data Index: 3109107 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2978. Min Range: -10.2978
Max Act: 9.4853. Min Act: -0.1700
Data Index: 474586 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2978. Min Range: -10.2978
Max Act: 9.4853. Min Act: -0.1700
Data Index: 1239149 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2978. Min Range: -10.2978
Max Act: 9.4228. Min Act: -0.1700
Data Index: 7473219 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2978. Min Range: -10.2978
Max Act: 9.4228. Min Act: -0.1700
Data Index: 5567909 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2978. Min Range: -10.2978
Max Act: 9.4228. Min Act: -0.1700
Data Index: 6829086 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2978. Min Range: -10.2978
Max Act: 9.3603. Min Act: -0.1700
Data Index: 7116846 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2978. Min Range: -10.2978
Max Act: 9.4228. Min Act: -0.1700
Data Index: 8672409 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2978. Min Range: -10.2978
Max Act: 9.3603. Min Act: -0.1700
Data Index: 2444947 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2978. Min Range: -10.2978
Max Act: 9.2978. Min Act: -0.1700
Data Index: 4577250 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2978. Min Range: -10.2978
Max Act: 9.2978. Min Act: -0.1700
Data Index: 5623300 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2978. Min Range: -10.2978
Max Act: 9.2353. Min Act: -0.1700
Data Index: 4565916 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19