Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 938 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9414. Min Range: -9.9414
Max Act: 9.9414. Min Act: -0.1700
Data Index: 944277 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9414. Min Range: -9.9414
Max Act: 9.6914. Min Act: -0.1700
Data Index: 2022775 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9414. Min Range: -9.9414
Max Act: 9.6289. Min Act: -0.1700
Data Index: 5959822 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9414. Min Range: -9.9414
Max Act: 9.5039. Min Act: -0.1699
Data Index: 6330270 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9414. Min Range: -9.9414
Max Act: 9.4414. Min Act: -0.1700
Data Index: 3180384 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9414. Min Range: -9.9414
Max Act: 9.4414. Min Act: -0.1700
Data Index: 5794916 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9414. Min Range: -9.9414
Max Act: 9.3164. Min Act: -0.1700
Data Index: 4493292 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9414. Min Range: -9.9414
Max Act: 9.3164. Min Act: -0.1700
Data Index: 3162603 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9414. Min Range: -9.9414
Max Act: 9.2539. Min Act: -0.1700
Data Index: 7143068 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9414. Min Range: -9.9414
Max Act: 9.3164. Min Act: -0.1700
Data Index: 547010 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9414. Min Range: -9.9414
Max Act: 9.3164. Min Act: -0.1699
Data Index: 5615673 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9414. Min Range: -9.9414
Max Act: 9.2539. Min Act: -0.1700
Data Index: 3870268 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9414. Min Range: -9.9414
Max Act: 9.2539. Min Act: -0.1700
Data Index: 1910686 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9414. Min Range: -9.9414
Max Act: 9.2539. Min Act: -0.1700
Data Index: 2972376 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9414. Min Range: -9.9414
Max Act: 9.1914. Min Act: -0.1700
Data Index: 4668027 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9414. Min Range: -9.9414
Max Act: 9.1914. Min Act: -0.1700
Data Index: 584983 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9414. Min Range: -9.9414
Max Act: 9.2539. Min Act: -0.1700
Data Index: 6100791 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9414. Min Range: -9.9414
Max Act: 9.1914. Min Act: -0.1700
Data Index: 619145 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9414. Min Range: -9.9414
Max Act: 9.1914. Min Act: -0.1700
Data Index: 1062898 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9414. Min Range: -9.9414
Max Act: 9.1914. Min Act: -0.1700
Data Index: 6342791 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #19