Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3438 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4353. Min Range: -8.4353
Max Act: 8.4353. Min Act: -0.1700
Data Index: 6176919 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4353. Min Range: -8.4353
Max Act: 8.2478. Min Act: -0.1700
Data Index: 8092044 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4353. Min Range: -8.4353
Max Act: 8.1228. Min Act: -0.1700
Data Index: 344493 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4353. Min Range: -8.4353
Max Act: 8.0603. Min Act: -0.1700
Data Index: 1416245 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4353. Min Range: -8.4353
Max Act: 8.0603. Min Act: -0.1700
Data Index: 8163269 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4353. Min Range: -8.4353
Max Act: 8.0603. Min Act: -0.1700
Data Index: 7214597 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4353. Min Range: -8.4353
Max Act: 8.0603. Min Act: -0.1700
Data Index: 2383005 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4353. Min Range: -8.4353
Max Act: 8.0603. Min Act: -0.1700
Data Index: 8531394 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4353. Min Range: -8.4353
Max Act: 7.9978. Min Act: -0.1700
Data Index: 5296354 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4353. Min Range: -8.4353
Max Act: 7.9978. Min Act: -0.1700
Data Index: 3478830 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4353. Min Range: -8.4353
Max Act: 7.9353. Min Act: -0.1700
Data Index: 7729980 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4353. Min Range: -8.4353
Max Act: 7.8728. Min Act: -0.1700
Data Index: 4278784 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4353. Min Range: -8.4353
Max Act: 7.8728. Min Act: -0.1700
Data Index: 2287454 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4353. Min Range: -8.4353
Max Act: 7.8103. Min Act: -0.1700
Data Index: 563918 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4353. Min Range: -8.4353
Max Act: 7.8728. Min Act: -0.1700
Data Index: 5795651 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4353. Min Range: -8.4353
Max Act: 7.8103. Min Act: -0.1700
Data Index: 2732300 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4353. Min Range: -8.4353
Max Act: 7.8103. Min Act: -0.1700
Data Index: 719766 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4353. Min Range: -8.4353
Max Act: 7.8103. Min Act: -0.1700
Data Index: 7519705 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4353. Min Range: -8.4353
Max Act: 7.7478. Min Act: -0.1700
Data Index: 74451 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4353. Min Range: -8.4353
Max Act: 7.6853. Min Act: -0.1700
Data Index: 5131105 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19