Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4557 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1041. Min Range: -6.1041
Max Act: 6.1041. Min Act: -0.1700
Data Index: 3842115 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1041. Min Range: -6.1041
Max Act: 5.9478. Min Act: -0.1700
Data Index: 119937 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1041. Min Range: -6.1041
Max Act: 5.9791. Min Act: -0.1700
Data Index: 8209268 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1041. Min Range: -6.1041
Max Act: 5.8541. Min Act: -0.1700
Data Index: 5731880 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1041. Min Range: -6.1041
Max Act: 5.8228. Min Act: -0.1700
Data Index: 2116677 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1041. Min Range: -6.1041
Max Act: 5.7291. Min Act: -0.1700
Data Index: 2411146 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1041. Min Range: -6.1041
Max Act: 5.7291. Min Act: -0.1700
Data Index: 469700 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1041. Min Range: -6.1041
Max Act: 5.6978. Min Act: -0.1700
Data Index: 4835583 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1041. Min Range: -6.1041
Max Act: 5.6978. Min Act: -0.1700
Data Index: 6844812 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1041. Min Range: -6.1041
Max Act: 5.6666. Min Act: -0.1700
Data Index: 6718094 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1041. Min Range: -6.1041
Max Act: 5.6353. Min Act: -0.1700
Data Index: 5246612 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1041. Min Range: -6.1041
Max Act: 5.6353. Min Act: -0.1700
Data Index: 8504532 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1041. Min Range: -6.1041
Max Act: 5.6041. Min Act: -0.1700
Data Index: 2153342 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1041. Min Range: -6.1041
Max Act: 5.5728. Min Act: -0.1700
Data Index: 2035869 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1041. Min Range: -6.1041
Max Act: 5.5728. Min Act: -0.1700
Data Index: 836793 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1041. Min Range: -6.1041
Max Act: 5.5728. Min Act: -0.1700
Data Index: 210627 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1041. Min Range: -6.1041
Max Act: 5.5416. Min Act: -0.1700
Data Index: 1033667 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1041. Min Range: -6.1041
Max Act: 5.5416. Min Act: -0.1700
Data Index: 4230599 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1041. Min Range: -6.1041
Max Act: 5.5103. Min Act: -0.1700
Data Index: 4832033 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1041. Min Range: -6.1041
Max Act: 5.4478. Min Act: -0.1700
Data Index: 7888730 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19