Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2836 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8101. Min Range: -5.8101
Max Act: 5.8101. Min Act: -0.1700
Data Index: 6315880 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8101. Min Range: -5.8101
Max Act: 5.7163. Min Act: -0.1700
Data Index: 3901905 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8101. Min Range: -5.8101
Max Act: 5.6538. Min Act: -0.1700
Data Index: 8565276 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8101. Min Range: -5.8101
Max Act: 5.6226. Min Act: -0.1700
Data Index: 2159717 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8101. Min Range: -5.8101
Max Act: 5.5913. Min Act: -0.1700
Data Index: 2723827 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8101. Min Range: -5.8101
Max Act: 5.5913. Min Act: -0.1700
Data Index: 328640 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8101. Min Range: -5.8101
Max Act: 5.5288. Min Act: -0.1700
Data Index: 8572588 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8101. Min Range: -5.8101
Max Act: 5.4976. Min Act: -0.1700
Data Index: 130623 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8101. Min Range: -5.8101
Max Act: 5.4351. Min Act: -0.1700
Data Index: 3404366 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8101. Min Range: -5.8101
Max Act: 5.4351. Min Act: -0.1700
Data Index: 5074356 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8101. Min Range: -5.8101
Max Act: 5.4351. Min Act: -0.1700
Data Index: 2629466 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8101. Min Range: -5.8101
Max Act: 5.4351. Min Act: -0.1700
Data Index: 2449564 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8101. Min Range: -5.8101
Max Act: 5.4351. Min Act: -0.1700
Data Index: 7884776 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8101. Min Range: -5.8101
Max Act: 5.4038. Min Act: -0.1700
Data Index: 8640146 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8101. Min Range: -5.8101
Max Act: 5.4351. Min Act: -0.1700
Data Index: 6274442 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8101. Min Range: -5.8101
Max Act: 5.4351. Min Act: -0.1700
Data Index: 3760853 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8101. Min Range: -5.8101
Max Act: 5.4038. Min Act: -0.1700
Data Index: 3777704 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8101. Min Range: -5.8101
Max Act: 5.4038. Min Act: -0.1700
Data Index: 259593 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8101. Min Range: -5.8101
Max Act: 5.4038. Min Act: -0.1700
Data Index: 2268906 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8101. Min Range: -5.8101
Max Act: 5.3726. Min Act: -0.1700
Data Index: 697771 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19