Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3267 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6314. Min Range: -6.6314
Max Act: 6.6314. Min Act: -0.1700
Data Index: 8156798 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6314. Min Range: -6.6314
Max Act: 6.6002. Min Act: -0.1700
Data Index: 2810714 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6314. Min Range: -6.6314
Max Act: 6.5064. Min Act: -0.1700
Data Index: 2865448 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6314. Min Range: -6.6314
Max Act: 6.4127. Min Act: -0.1700
Data Index: 8745487 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6314. Min Range: -6.6314
Max Act: 6.4127. Min Act: -0.1700
Data Index: 474638 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6314. Min Range: -6.6314
Max Act: 6.4127. Min Act: -0.1700
Data Index: 6423748 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6314. Min Range: -6.6314
Max Act: 6.3189. Min Act: -0.1700
Data Index: 4496899 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6314. Min Range: -6.6314
Max Act: 6.3189. Min Act: -0.1700
Data Index: 4078186 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6314. Min Range: -6.6314
Max Act: 6.3189. Min Act: -0.1700
Data Index: 3865584 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6314. Min Range: -6.6314
Max Act: 6.2564. Min Act: -0.1700
Data Index: 6085169 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6314. Min Range: -6.6314
Max Act: 6.2877. Min Act: -0.1700
Data Index: 3791928 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6314. Min Range: -6.6314
Max Act: 6.2564. Min Act: -0.1700
Data Index: 4627685 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6314. Min Range: -6.6314
Max Act: 6.2564. Min Act: -0.1700
Data Index: 1527646 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6314. Min Range: -6.6314
Max Act: 6.2252. Min Act: -0.1700
Data Index: 33736 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6314. Min Range: -6.6314
Max Act: 6.2252. Min Act: -0.1700
Data Index: 1993562 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6314. Min Range: -6.6314
Max Act: 6.1939. Min Act: -0.1700
Data Index: 4205594 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6314. Min Range: -6.6314
Max Act: 6.1627. Min Act: -0.1700
Data Index: 965121 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6314. Min Range: -6.6314
Max Act: 6.1627. Min Act: -0.1700
Data Index: 5831572 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6314. Min Range: -6.6314
Max Act: 6.1002. Min Act: -0.1700
Data Index: 1624495 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6314. Min Range: -6.6314
Max Act: 6.1002. Min Act: -0.1700
Data Index: 4706186 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19