Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4729 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2384. Min Range: -6.2384
Max Act: 6.2384. Min Act: -0.1700
Data Index: 5917423 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2384. Min Range: -6.2384
Max Act: 6.2384. Min Act: -0.1700
Data Index: 8587770 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2384. Min Range: -6.2384
Max Act: 5.9572. Min Act: -0.1700
Data Index: 6138552 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2384. Min Range: -6.2384
Max Act: 5.9884. Min Act: -0.1700
Data Index: 1311669 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2384. Min Range: -6.2384
Max Act: 5.9572. Min Act: -0.1700
Data Index: 1200846 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2384. Min Range: -6.2384
Max Act: 6.0197. Min Act: -0.1700
Data Index: 3593058 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2384. Min Range: -6.2384
Max Act: 5.9572. Min Act: -0.1700
Data Index: 7384429 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2384. Min Range: -6.2384
Max Act: 5.9572. Min Act: -0.1700
Data Index: 6423443 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2384. Min Range: -6.2384
Max Act: 5.9884. Min Act: -0.1700
Data Index: 4251688 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2384. Min Range: -6.2384
Max Act: 5.9572. Min Act: -0.1700
Data Index: 5868444 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2384. Min Range: -6.2384
Max Act: 5.8947. Min Act: -0.1700
Data Index: 4141551 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2384. Min Range: -6.2384
Max Act: 5.8947. Min Act: -0.1700
Data Index: 1185638 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2384. Min Range: -6.2384
Max Act: 5.8947. Min Act: -0.1700
Data Index: 1315115 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2384. Min Range: -6.2384
Max Act: 5.8947. Min Act: -0.1700
Data Index: 6063746 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2384. Min Range: -6.2384
Max Act: 5.8634. Min Act: -0.1700
Data Index: 7383239 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2384. Min Range: -6.2384
Max Act: 5.8634. Min Act: -0.1700
Data Index: 4141552 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2384. Min Range: -6.2384
Max Act: 5.8634. Min Act: -0.1700
Data Index: 7064848 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2384. Min Range: -6.2384
Max Act: 5.8322. Min Act: -0.1700
Data Index: 3135792 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2384. Min Range: -6.2384
Max Act: 5.8634. Min Act: -0.1700
Data Index: 3306765 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2384. Min Range: -6.2384
Max Act: 5.8322. Min Act: -0.1700
Data Index: 6523117 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19