Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4438 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2459. Min Range: -8.2459
Max Act: 8.2459. Min Act: -0.1700
Data Index: 7064703 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2459. Min Range: -8.2459
Max Act: 8.2459. Min Act: -0.1700
Data Index: 6770598 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2459. Min Range: -8.2459
Max Act: 8.1834. Min Act: -0.1700
Data Index: 997798 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2459. Min Range: -8.2459
Max Act: 8.1834. Min Act: -0.1700
Data Index: 3254416 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2459. Min Range: -8.2459
Max Act: 8.1209. Min Act: -0.1700
Data Index: 1246615 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2459. Min Range: -8.2459
Max Act: 7.9959. Min Act: -0.1700
Data Index: 7289765 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2459. Min Range: -8.2459
Max Act: 7.9647. Min Act: -0.1700
Data Index: 4029668 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2459. Min Range: -8.2459
Max Act: 7.9959. Min Act: -0.1700
Data Index: 4083008 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2459. Min Range: -8.2459
Max Act: 7.9647. Min Act: -0.1700
Data Index: 4449373 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2459. Min Range: -8.2459
Max Act: 7.9647. Min Act: -0.1700
Data Index: 4455369 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2459. Min Range: -8.2459
Max Act: 7.9647. Min Act: -0.1700
Data Index: 7142349 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2459. Min Range: -8.2459
Max Act: 7.9022. Min Act: -0.1700
Data Index: 3069994 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2459. Min Range: -8.2459
Max Act: 7.9022. Min Act: -0.1700
Data Index: 1344196 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2459. Min Range: -8.2459
Max Act: 7.9022. Min Act: -0.1700
Data Index: 501540 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2459. Min Range: -8.2459
Max Act: 7.8709. Min Act: -0.1700
Data Index: 4083007 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2459. Min Range: -8.2459
Max Act: 7.8397. Min Act: -0.1700
Data Index: 3020100 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2459. Min Range: -8.2459
Max Act: 7.8709. Min Act: -0.1700
Data Index: 3719512 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2459. Min Range: -8.2459
Max Act: 7.8397. Min Act: -0.1700
Data Index: 4951265 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2459. Min Range: -8.2459
Max Act: 7.8084. Min Act: -0.1700
Data Index: 5714765 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2459. Min Range: -8.2459
Max Act: 7.8397. Min Act: -0.1700
Data Index: 4083004 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19