Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3470 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5602. Min Range: -5.5602
Max Act: 5.5602. Min Act: -0.1700
Data Index: 3727390 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5602. Min Range: -5.5602
Max Act: 5.5290. Min Act: -0.1700
Data Index: 4654005 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5602. Min Range: -5.5602
Max Act: 5.4977. Min Act: -0.1700
Data Index: 3331738 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5602. Min Range: -5.5602
Max Act: 5.4352. Min Act: -0.1700
Data Index: 4636804 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5602. Min Range: -5.5602
Max Act: 5.4352. Min Act: -0.1700
Data Index: 8380406 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5602. Min Range: -5.5602
Max Act: 5.3727. Min Act: -0.1700
Data Index: 6245663 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5602. Min Range: -5.5602
Max Act: 5.3727. Min Act: -0.1700
Data Index: 6753798 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5602. Min Range: -5.5602
Max Act: 5.3727. Min Act: -0.1700
Data Index: 6249495 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5602. Min Range: -5.5602
Max Act: 5.3415. Min Act: -0.1700
Data Index: 8050666 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5602. Min Range: -5.5602
Max Act: 5.2790. Min Act: -0.1700
Data Index: 4622800 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5602. Min Range: -5.5602
Max Act: 5.2477. Min Act: -0.1700
Data Index: 1377320 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5602. Min Range: -5.5602
Max Act: 5.3102. Min Act: -0.1700
Data Index: 2550109 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5602. Min Range: -5.5602
Max Act: 5.2790. Min Act: -0.1700
Data Index: 702525 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5602. Min Range: -5.5602
Max Act: 5.3102. Min Act: -0.1700
Data Index: 2986981 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5602. Min Range: -5.5602
Max Act: 5.2790. Min Act: -0.1700
Data Index: 7387846 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5602. Min Range: -5.5602
Max Act: 5.2790. Min Act: -0.1700
Data Index: 517178 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5602. Min Range: -5.5602
Max Act: 5.2477. Min Act: -0.1700
Data Index: 1321998 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5602. Min Range: -5.5602
Max Act: 5.2165. Min Act: -0.1700
Data Index: 4449463 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5602. Min Range: -5.5602
Max Act: 5.2477. Min Act: -0.1700
Data Index: 7102 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5602. Min Range: -5.5602
Max Act: 5.2477. Min Act: -0.1700
Data Index: 6142788 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19