Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2982 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5122. Min Range: -10.5122
Max Act: 10.5122. Min Act: -0.1700
Data Index: 6972219 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5122. Min Range: -10.5122
Max Act: 10.1997. Min Act: -0.1700
Data Index: 2895403 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5122. Min Range: -10.5122
Max Act: 10.1997. Min Act: -0.1700
Data Index: 8106359 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5122. Min Range: -10.5122
Max Act: 9.8247. Min Act: -0.1700
Data Index: 4135290 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5122. Min Range: -10.5122
Max Act: 9.8247. Min Act: -0.1700
Data Index: 1727710 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5122. Min Range: -10.5122
Max Act: 9.7622. Min Act: -0.1700
Data Index: 7734868 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5122. Min Range: -10.5122
Max Act: 9.7622. Min Act: -0.1700
Data Index: 2728465 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5122. Min Range: -10.5122
Max Act: 9.6997. Min Act: -0.1700
Data Index: 5487839 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5122. Min Range: -10.5122
Max Act: 9.6997. Min Act: -0.1700
Data Index: 7479462 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5122. Min Range: -10.5122
Max Act: 9.7622. Min Act: -0.1700
Data Index: 801135 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5122. Min Range: -10.5122
Max Act: 9.6997. Min Act: -0.1700
Data Index: 2056952 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5122. Min Range: -10.5122
Max Act: 9.6372. Min Act: -0.1700
Data Index: 7326066 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5122. Min Range: -10.5122
Max Act: 9.6372. Min Act: -0.1700
Data Index: 5023550 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5122. Min Range: -10.5122
Max Act: 9.6372. Min Act: -0.1700
Data Index: 8287762 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5122. Min Range: -10.5122
Max Act: 9.6372. Min Act: -0.1700
Data Index: 8361447 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5122. Min Range: -10.5122
Max Act: 9.5747. Min Act: -0.1700
Data Index: 4683438 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5122. Min Range: -10.5122
Max Act: 9.5747. Min Act: -0.1700
Data Index: 6038546 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5122. Min Range: -10.5122
Max Act: 9.5122. Min Act: -0.1700
Data Index: 2382176 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5122. Min Range: -10.5122
Max Act: 9.5122. Min Act: -0.1700
Data Index: 7161421 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5122. Min Range: -10.5122
Max Act: 9.4497. Min Act: -0.1700
Data Index: 925839 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19