Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3048. Min Range: -6.3048
Max Act: 6.3048. Min Act: -0.1700
Data Index: 1845317 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3048. Min Range: -6.3048
Max Act: 6.1486. Min Act: -0.1700
Data Index: 5615263 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3048. Min Range: -6.3048
Max Act: 6.1173. Min Act: -0.1700
Data Index: 5227494 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3048. Min Range: -6.3048
Max Act: 5.9923. Min Act: -0.1700
Data Index: 4141943 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3048. Min Range: -6.3048
Max Act: 5.9611. Min Act: -0.1700
Data Index: 5707587 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3048. Min Range: -6.3048
Max Act: 5.9298. Min Act: -0.1700
Data Index: 35803 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3048. Min Range: -6.3048
Max Act: 5.8986. Min Act: -0.1700
Data Index: 5873053 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3048. Min Range: -6.3048
Max Act: 5.8986. Min Act: -0.1700
Data Index: 5421847 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3048. Min Range: -6.3048
Max Act: 5.8986. Min Act: -0.1700
Data Index: 6619215 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3048. Min Range: -6.3048
Max Act: 5.8361. Min Act: -0.1700
Data Index: 2648303 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3048. Min Range: -6.3048
Max Act: 5.8673. Min Act: -0.1700
Data Index: 6704297 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3048. Min Range: -6.3048
Max Act: 5.8986. Min Act: -0.1700
Data Index: 7063107 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3048. Min Range: -6.3048
Max Act: 5.8673. Min Act: -0.1700
Data Index: 5567196 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3048. Min Range: -6.3048
Max Act: 5.8361. Min Act: -0.1700
Data Index: 5414662 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3048. Min Range: -6.3048
Max Act: 5.8048. Min Act: -0.1700
Data Index: 7567694 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3048. Min Range: -6.3048
Max Act: 5.8048. Min Act: -0.1700
Data Index: 3983780 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3048. Min Range: -6.3048
Max Act: 5.8048. Min Act: -0.1700
Data Index: 1800533 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3048. Min Range: -6.3048
Max Act: 5.8048. Min Act: -0.1700
Data Index: 4508153 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3048. Min Range: -6.3048
Max Act: 5.8048. Min Act: -0.1700
Data Index: 6763324 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3048. Min Range: -6.3048
Max Act: 5.8048. Min Act: -0.1700
Data Index: 7917575 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19