Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1294 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8872. Min Range: -3.8872
Max Act: 3.8872. Min Act: -0.1700
Data Index: 2526760 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8872. Min Range: -3.8872
Max Act: 3.7934. Min Act: -0.1700
Data Index: 4338368 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8872. Min Range: -3.8872
Max Act: 3.7465. Min Act: -0.1700
Data Index: 7346814 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8872. Min Range: -3.8872
Max Act: 3.7465. Min Act: -0.1700
Data Index: 1110886 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8872. Min Range: -3.8872
Max Act: 3.7152. Min Act: -0.1700
Data Index: 2072871 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8872. Min Range: -3.8872
Max Act: 3.7152. Min Act: -0.1700
Data Index: 6283420 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8872. Min Range: -3.8872
Max Act: 3.6526. Min Act: -0.1700
Data Index: 5008919 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8872. Min Range: -3.8872
Max Act: 3.6526. Min Act: -0.1700
Data Index: 4776475 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8872. Min Range: -3.8872
Max Act: 3.6213. Min Act: -0.1700
Data Index: 4867934 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8872. Min Range: -3.8872
Max Act: 3.5900. Min Act: -0.1700
Data Index: 4913357 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8872. Min Range: -3.8872
Max Act: 3.5900. Min Act: -0.1700
Data Index: 2431898 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8872. Min Range: -3.8872
Max Act: 3.5744. Min Act: -0.1700
Data Index: 6788899 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8872. Min Range: -3.8872
Max Act: 3.5744. Min Act: -0.1700
Data Index: 1891759 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8872. Min Range: -3.8872
Max Act: 3.5587. Min Act: -0.1700
Data Index: 7448298 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8872. Min Range: -3.8872
Max Act: 3.5431. Min Act: -0.1700
Data Index: 673449 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8872. Min Range: -3.8872
Max Act: 3.5431. Min Act: -0.1700
Data Index: 7214207 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8872. Min Range: -3.8872
Max Act: 3.5274. Min Act: -0.1700
Data Index: 8330312 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8872. Min Range: -3.8872
Max Act: 3.5117. Min Act: -0.1700
Data Index: 7677599 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8872. Min Range: -3.8872
Max Act: 3.5117. Min Act: -0.1700
Data Index: 3703923 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8872. Min Range: -3.8872
Max Act: 3.5117. Min Act: -0.1700
Data Index: 5081446 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19