Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1021 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3080. Min Range: -6.3080
Max Act: 6.3080. Min Act: -0.1700
Data Index: 7668420 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3080. Min Range: -6.3080
Max Act: 5.8705. Min Act: -0.1700
Data Index: 8419717 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3080. Min Range: -6.3080
Max Act: 5.6205. Min Act: -0.1700
Data Index: 277442 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3080. Min Range: -6.3080
Max Act: 5.6518. Min Act: -0.1700
Data Index: 277443 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3080. Min Range: -6.3080
Max Act: 5.6205. Min Act: -0.1700
Data Index: 3548806 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3080. Min Range: -6.3080
Max Act: 5.6205. Min Act: -0.1700
Data Index: 3098417 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3080. Min Range: -6.3080
Max Act: 5.5893. Min Act: -0.1700
Data Index: 277452 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3080. Min Range: -6.3080
Max Act: 5.5893. Min Act: -0.1700
Data Index: 351090 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3080. Min Range: -6.3080
Max Act: 5.5893. Min Act: -0.1700
Data Index: 3072634 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3080. Min Range: -6.3080
Max Act: 5.5580. Min Act: -0.1700
Data Index: 3836558 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3080. Min Range: -6.3080
Max Act: 5.5268. Min Act: -0.1700
Data Index: 2921508 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3080. Min Range: -6.3080
Max Act: 5.5268. Min Act: -0.1700
Data Index: 136088 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3080. Min Range: -6.3080
Max Act: 5.5268. Min Act: -0.1700
Data Index: 5462892 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3080. Min Range: -6.3080
Max Act: 5.5268. Min Act: -0.1700
Data Index: 3540728 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3080. Min Range: -6.3080
Max Act: 5.5268. Min Act: -0.1700
Data Index: 948029 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3080. Min Range: -6.3080
Max Act: 5.5268. Min Act: -0.1700
Data Index: 3131201 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3080. Min Range: -6.3080
Max Act: 5.4955. Min Act: -0.1700
Data Index: 1694004 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3080. Min Range: -6.3080
Max Act: 5.4643. Min Act: -0.1700
Data Index: 179493 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3080. Min Range: -6.3080
Max Act: 5.4643. Min Act: -0.1700
Data Index: 4988995 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3080. Min Range: -6.3080
Max Act: 5.4955. Min Act: -0.1700
Data Index: 2360255 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19