Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3534 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4343. Min Range: -6.4343
Max Act: 6.4343. Min Act: -0.1700
Data Index: 2483878 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4343. Min Range: -6.4343
Max Act: 6.3093. Min Act: -0.1700
Data Index: 2150580 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4343. Min Range: -6.4343
Max Act: 6.2781. Min Act: -0.1700
Data Index: 4965746 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4343. Min Range: -6.4343
Max Act: 6.2468. Min Act: -0.1700
Data Index: 8404336 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4343. Min Range: -6.4343
Max Act: 6.2468. Min Act: -0.1700
Data Index: 3074829 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4343. Min Range: -6.4343
Max Act: 6.1843. Min Act: -0.1700
Data Index: 5384938 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4343. Min Range: -6.4343
Max Act: 6.1843. Min Act: -0.1700
Data Index: 1932927 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4343. Min Range: -6.4343
Max Act: 6.1531. Min Act: -0.1700
Data Index: 2216304 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4343. Min Range: -6.4343
Max Act: 6.1218. Min Act: -0.1700
Data Index: 7023175 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4343. Min Range: -6.4343
Max Act: 6.1218. Min Act: -0.1700
Data Index: 7051901 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4343. Min Range: -6.4343
Max Act: 6.1218. Min Act: -0.1700
Data Index: 5115867 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4343. Min Range: -6.4343
Max Act: 6.0593. Min Act: -0.1700
Data Index: 3407891 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4343. Min Range: -6.4343
Max Act: 6.0906. Min Act: -0.1700
Data Index: 6731860 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4343. Min Range: -6.4343
Max Act: 6.0593. Min Act: -0.1700
Data Index: 2006823 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4343. Min Range: -6.4343
Max Act: 6.0281. Min Act: -0.1700
Data Index: 3300898 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4343. Min Range: -6.4343
Max Act: 6.0593. Min Act: -0.1700
Data Index: 8011816 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4343. Min Range: -6.4343
Max Act: 6.0593. Min Act: -0.1700
Data Index: 2321017 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4343. Min Range: -6.4343
Max Act: 5.9968. Min Act: -0.1700
Data Index: 6159897 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4343. Min Range: -6.4343
Max Act: 5.9968. Min Act: -0.1700
Data Index: 7847779 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4343. Min Range: -6.4343
Max Act: 5.9968. Min Act: -0.1700
Data Index: 1005080 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19