Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2963 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5338. Min Range: -9.5338
Max Act: 9.5338. Min Act: -0.1700
Data Index: 2309274 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5338. Min Range: -9.5338
Max Act: 9.4088. Min Act: -0.1700
Data Index: 6040169 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5338. Min Range: -9.5338
Max Act: 9.3463. Min Act: -0.1700
Data Index: 3959222 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5338. Min Range: -9.5338
Max Act: 9.3463. Min Act: -0.1700
Data Index: 2411298 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5338. Min Range: -9.5338
Max Act: 9.2838. Min Act: -0.1700
Data Index: 903513 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5338. Min Range: -9.5338
Max Act: 9.2213. Min Act: -0.1700
Data Index: 6157809 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5338. Min Range: -9.5338
Max Act: 9.1588. Min Act: -0.1700
Data Index: 220526 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5338. Min Range: -9.5338
Max Act: 9.1588. Min Act: -0.1700
Data Index: 2506256 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5338. Min Range: -9.5338
Max Act: 9.1588. Min Act: -0.1700
Data Index: 2982203 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5338. Min Range: -9.5338
Max Act: 9.1588. Min Act: -0.1700
Data Index: 7005543 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5338. Min Range: -9.5338
Max Act: 9.0963. Min Act: -0.1700
Data Index: 8077000 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5338. Min Range: -9.5338
Max Act: 9.0338. Min Act: -0.1700
Data Index: 3845290 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5338. Min Range: -9.5338
Max Act: 9.0338. Min Act: -0.1700
Data Index: 5319065 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5338. Min Range: -9.5338
Max Act: 9.0338. Min Act: -0.1700
Data Index: 1088252 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5338. Min Range: -9.5338
Max Act: 9.0338. Min Act: -0.1700
Data Index: 972171 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5338. Min Range: -9.5338
Max Act: 9.0338. Min Act: -0.1700
Data Index: 4606054 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5338. Min Range: -9.5338
Max Act: 9.0338. Min Act: -0.1700
Data Index: 935479 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5338. Min Range: -9.5338
Max Act: 9.0338. Min Act: -0.1700
Data Index: 6062853 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5338. Min Range: -9.5338
Max Act: 9.0338. Min Act: -0.1700
Data Index: 2116026 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5338. Min Range: -9.5338
Max Act: 8.9713. Min Act: -0.1700
Data Index: 314841 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19