Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4932 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8079. Min Range: -4.8079
Max Act: 4.8079. Min Act: -0.1700
Data Index: 6980821 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8079. Min Range: -4.8079
Max Act: 4.6204. Min Act: -0.1691
Data Index: 2018506 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8079. Min Range: -4.8079
Max Act: 4.6204. Min Act: -0.1700
Data Index: 218821 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8079. Min Range: -4.8079
Max Act: 4.6204. Min Act: -0.1700
Data Index: 196285 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8079. Min Range: -4.8079
Max Act: 4.5892. Min Act: -0.1700
Data Index: 6292293 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8079. Min Range: -4.8079
Max Act: 4.4954. Min Act: -0.1700
Data Index: 8031620 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8079. Min Range: -4.8079
Max Act: 4.4016. Min Act: -0.1700
Data Index: 6588299 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8079. Min Range: -4.8079
Max Act: 4.3704. Min Act: -0.1700
Data Index: 2018510 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8079. Min Range: -4.8079
Max Act: 4.4016. Min Act: -0.1700
Data Index: 927550 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8079. Min Range: -4.8079
Max Act: 4.4016. Min Act: -0.1700
Data Index: 2018509 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8079. Min Range: -4.8079
Max Act: 4.4016. Min Act: -0.1700
Data Index: 2018514 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8079. Min Range: -4.8079
Max Act: 4.3391. Min Act: -0.1688
Data Index: 2018505 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8079. Min Range: -4.8079
Max Act: 4.3704. Min Act: -0.1700
Data Index: 5527181 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8079. Min Range: -4.8079
Max Act: 4.3391. Min Act: -0.1700
Data Index: 2412104 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8079. Min Range: -4.8079
Max Act: 4.3704. Min Act: -0.1700
Data Index: 1197660 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8079. Min Range: -4.8079
Max Act: 4.3704. Min Act: -0.1700
Data Index: 27366 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8079. Min Range: -4.8079
Max Act: 4.3391. Min Act: -0.1700
Data Index: 2018507 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8079. Min Range: -4.8079
Max Act: 4.3391. Min Act: -0.1700
Data Index: 159249 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8079. Min Range: -4.8079
Max Act: 4.3079. Min Act: -0.1700
Data Index: 6826086 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8079. Min Range: -4.8079
Max Act: 4.3079. Min Act: -0.1700
Data Index: 2796319 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19