Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1885 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3895. Min Range: -3.3895
Max Act: 3.3895. Min Act: -0.1700
Data Index: 2229562 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3895. Min Range: -3.3895
Max Act: 3.3424. Min Act: -0.1700
Data Index: 6739591 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3895. Min Range: -3.3895
Max Act: 3.3267. Min Act: -0.1700
Data Index: 4818119 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3895. Min Range: -3.3895
Max Act: 3.2953. Min Act: -0.1700
Data Index: 2282135 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3895. Min Range: -3.3895
Max Act: 3.3110. Min Act: -0.1700
Data Index: 2163224 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3895. Min Range: -3.3895
Max Act: 3.3110. Min Act: -0.1700
Data Index: 6191456 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3895. Min Range: -3.3895
Max Act: 3.3110. Min Act: -0.1700
Data Index: 2757362 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3895. Min Range: -3.3895
Max Act: 3.2953. Min Act: -0.1700
Data Index: 379869 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3895. Min Range: -3.3895
Max Act: 3.2953. Min Act: -0.1700
Data Index: 3846972 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3895. Min Range: -3.3895
Max Act: 3.2639. Min Act: -0.1700
Data Index: 1299789 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3895. Min Range: -3.3895
Max Act: 3.2325. Min Act: -0.1700
Data Index: 1038457 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3895. Min Range: -3.3895
Max Act: 3.2482. Min Act: -0.1700
Data Index: 4769060 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3895. Min Range: -3.3895
Max Act: 3.2482. Min Act: -0.1700
Data Index: 1892949 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3895. Min Range: -3.3895
Max Act: 3.2482. Min Act: -0.1700
Data Index: 2364877 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3895. Min Range: -3.3895
Max Act: 3.2325. Min Act: -0.1700
Data Index: 3933401 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3895. Min Range: -3.3895
Max Act: 3.2482. Min Act: -0.1700
Data Index: 3871208 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3895. Min Range: -3.3895
Max Act: 3.2168. Min Act: -0.1700
Data Index: 3804323 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3895. Min Range: -3.3895
Max Act: 3.2325. Min Act: -0.1700
Data Index: 3532642 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3895. Min Range: -3.3895
Max Act: 3.2482. Min Act: -0.1700
Data Index: 3335219 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3895. Min Range: -3.3895
Max Act: 3.2168. Min Act: -0.1700
Data Index: 1057310 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19