Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4504 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3106. Min Range: -5.3106
Max Act: 5.3106. Min Act: -0.1700
Data Index: 5808665 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3106. Min Range: -5.3106
Max Act: 5.2481. Min Act: -0.1700
Data Index: 6649061 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3106. Min Range: -5.3106
Max Act: 5.1543. Min Act: -0.1700
Data Index: 829235 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3106. Min Range: -5.3106
Max Act: 5.1231. Min Act: -0.1700
Data Index: 1295167 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3106. Min Range: -5.3106
Max Act: 5.1231. Min Act: -0.1700
Data Index: 6259250 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3106. Min Range: -5.3106
Max Act: 5.0918. Min Act: -0.1700
Data Index: 731228 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3106. Min Range: -5.3106
Max Act: 5.0918. Min Act: -0.1700
Data Index: 8452812 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3106. Min Range: -5.3106
Max Act: 5.0918. Min Act: -0.1700
Data Index: 8007858 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3106. Min Range: -5.3106
Max Act: 5.1231. Min Act: -0.1700
Data Index: 4918022 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3106. Min Range: -5.3106
Max Act: 5.0918. Min Act: -0.1700
Data Index: 6528312 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3106. Min Range: -5.3106
Max Act: 5.0918. Min Act: -0.1700
Data Index: 4831723 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3106. Min Range: -5.3106
Max Act: 5.0918. Min Act: -0.1700
Data Index: 3319209 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3106. Min Range: -5.3106
Max Act: 5.0918. Min Act: -0.1700
Data Index: 1943044 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3106. Min Range: -5.3106
Max Act: 5.0918. Min Act: -0.1700
Data Index: 1916402 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3106. Min Range: -5.3106
Max Act: 5.0918. Min Act: -0.1700
Data Index: 3707485 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3106. Min Range: -5.3106
Max Act: 5.0918. Min Act: -0.1700
Data Index: 8457350 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3106. Min Range: -5.3106
Max Act: 5.0606. Min Act: -0.1700
Data Index: 4899958 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3106. Min Range: -5.3106
Max Act: 5.0606. Min Act: -0.1700
Data Index: 5965795 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3106. Min Range: -5.3106
Max Act: 5.0606. Min Act: -0.1700
Data Index: 4000827 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3106. Min Range: -5.3106
Max Act: 5.0606. Min Act: -0.1700
Data Index: 7062930 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19