Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4800 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0372. Min Range: -7.0372
Max Act: 7.0372. Min Act: -0.1700
Data Index: 1567240 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0372. Min Range: -7.0372
Max Act: 6.9434. Min Act: -0.1700
Data Index: 175146 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0372. Min Range: -7.0372
Max Act: 6.9434. Min Act: -0.1700
Data Index: 5298149 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0372. Min Range: -7.0372
Max Act: 6.9434. Min Act: -0.1700
Data Index: 2646752 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0372. Min Range: -7.0372
Max Act: 6.8497. Min Act: -0.1700
Data Index: 4420522 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0372. Min Range: -7.0372
Max Act: 6.8497. Min Act: -0.1700
Data Index: 4930953 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0372. Min Range: -7.0372
Max Act: 6.7872. Min Act: -0.1700
Data Index: 4700388 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0372. Min Range: -7.0372
Max Act: 6.7872. Min Act: -0.1700
Data Index: 533605 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0372. Min Range: -7.0372
Max Act: 6.7559. Min Act: -0.1700
Data Index: 6185162 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0372. Min Range: -7.0372
Max Act: 6.7559. Min Act: -0.1700
Data Index: 2408943 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0372. Min Range: -7.0372
Max Act: 6.6934. Min Act: -0.1700
Data Index: 1710637 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0372. Min Range: -7.0372
Max Act: 6.7247. Min Act: -0.1700
Data Index: 2881629 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0372. Min Range: -7.0372
Max Act: 6.6622. Min Act: -0.1700
Data Index: 8574942 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0372. Min Range: -7.0372
Max Act: 6.6934. Min Act: -0.1700
Data Index: 2049107 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0372. Min Range: -7.0372
Max Act: 6.7247. Min Act: -0.1700
Data Index: 6329588 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0372. Min Range: -7.0372
Max Act: 6.6622. Min Act: -0.1700
Data Index: 4107944 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0372. Min Range: -7.0372
Max Act: 6.6622. Min Act: -0.1700
Data Index: 7612535 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0372. Min Range: -7.0372
Max Act: 6.6309. Min Act: -0.1700
Data Index: 5158424 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0372. Min Range: -7.0372
Max Act: 6.5684. Min Act: -0.1700
Data Index: 4064921 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0372. Min Range: -7.0372
Max Act: 6.6309. Min Act: -0.1700
Data Index: 5917333 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19