Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 447 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4978. Min Range: -10.4978
Max Act: 10.4978. Min Act: -0.1700
Data Index: 715171 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4978. Min Range: -10.4978
Max Act: 9.5603. Min Act: -0.1700
Data Index: 4567902 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4978. Min Range: -10.4978
Max Act: 9.1853. Min Act: -0.1700
Data Index: 4181320 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4978. Min Range: -10.4978
Max Act: 9.1853. Min Act: -0.1700
Data Index: 6646718 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4978. Min Range: -10.4978
Max Act: 8.9978. Min Act: -0.1700
Data Index: 7083707 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4978. Min Range: -10.4978
Max Act: 8.9978. Min Act: -0.1700
Data Index: 1342649 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4978. Min Range: -10.4978
Max Act: 8.9353. Min Act: -0.1700
Data Index: 5092269 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4978. Min Range: -10.4978
Max Act: 8.8728. Min Act: -0.1700
Data Index: 8291800 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4978. Min Range: -10.4978
Max Act: 8.8103. Min Act: -0.1700
Data Index: 4107032 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4978. Min Range: -10.4978
Max Act: 8.8103. Min Act: -0.1700
Data Index: 747007 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4978. Min Range: -10.4978
Max Act: 8.8103. Min Act: -0.1700
Data Index: 1889006 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4978. Min Range: -10.4978
Max Act: 8.8103. Min Act: -0.1700
Data Index: 7873565 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4978. Min Range: -10.4978
Max Act: 8.8103. Min Act: -0.1700
Data Index: 4696171 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4978. Min Range: -10.4978
Max Act: 8.7478. Min Act: -0.1700
Data Index: 1685811 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4978. Min Range: -10.4978
Max Act: 8.7478. Min Act: -0.1700
Data Index: 5769706 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4978. Min Range: -10.4978
Max Act: 8.6853. Min Act: -0.1700
Data Index: 5876970 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4978. Min Range: -10.4978
Max Act: 8.6853. Min Act: -0.1700
Data Index: 3435080 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4978. Min Range: -10.4978
Max Act: 8.6853. Min Act: -0.1700
Data Index: 7587624 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4978. Min Range: -10.4978
Max Act: 8.6228. Min Act: -0.1700
Data Index: 1611297 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4978. Min Range: -10.4978
Max Act: 8.6228. Min Act: -0.1700
Data Index: 4010030 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19