Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4443 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3829. Min Range: -10.3829
Max Act: 10.3829. Min Act: -0.1700
Data Index: 3221704 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3829. Min Range: -10.3829
Max Act: 10.1954. Min Act: -0.1700
Data Index: 4458150 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3829. Min Range: -10.3829
Max Act: 10.1954. Min Act: -0.1700
Data Index: 8137432 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3829. Min Range: -10.3829
Max Act: 10.1329. Min Act: -0.1700
Data Index: 6275848 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3829. Min Range: -10.3829
Max Act: 10.1329. Min Act: -0.1700
Data Index: 3230374 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3829. Min Range: -10.3829
Max Act: 10.0079. Min Act: -0.1700
Data Index: 2024060 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3829. Min Range: -10.3829
Max Act: 9.9454. Min Act: -0.1700
Data Index: 1327716 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3829. Min Range: -10.3829
Max Act: 9.8829. Min Act: -0.1700
Data Index: 5827938 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3829. Min Range: -10.3829
Max Act: 9.9454. Min Act: -0.1700
Data Index: 2372774 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3829. Min Range: -10.3829
Max Act: 9.9454. Min Act: -0.1700
Data Index: 8710636 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3829. Min Range: -10.3829
Max Act: 9.8829. Min Act: -0.1700
Data Index: 3082747 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3829. Min Range: -10.3829
Max Act: 9.8829. Min Act: -0.1700
Data Index: 789972 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3829. Min Range: -10.3829
Max Act: 9.8829. Min Act: -0.1700
Data Index: 4783458 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3829. Min Range: -10.3829
Max Act: 9.8204. Min Act: -0.1700
Data Index: 5741778 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3829. Min Range: -10.3829
Max Act: 9.8204. Min Act: -0.1700
Data Index: 2049295 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3829. Min Range: -10.3829
Max Act: 9.8204. Min Act: -0.1700
Data Index: 204345 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3829. Min Range: -10.3829
Max Act: 9.8204. Min Act: -0.1700
Data Index: 6444832 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3829. Min Range: -10.3829
Max Act: 9.8204. Min Act: -0.1700
Data Index: 7187334 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3829. Min Range: -10.3829
Max Act: 9.8204. Min Act: -0.1700
Data Index: 8004465 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3829. Min Range: -10.3829
Max Act: 9.8204. Min Act: -0.1700
Data Index: 4572669 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19