Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1759 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6608. Min Range: -6.6608
Max Act: 6.6608. Min Act: -0.1700
Data Index: 3925979 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6608. Min Range: -6.6608
Max Act: 6.4420. Min Act: -0.1700
Data Index: 3101034 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6608. Min Range: -6.6608
Max Act: 6.2545. Min Act: -0.1700
Data Index: 871558 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6608. Min Range: -6.6608
Max Act: 6.2858. Min Act: -0.1700
Data Index: 3814702 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6608. Min Range: -6.6608
Max Act: 6.0983. Min Act: -0.1700
Data Index: 1673796 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6608. Min Range: -6.6608
Max Act: 6.0983. Min Act: -0.1700
Data Index: 6002456 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6608. Min Range: -6.6608
Max Act: 6.0983. Min Act: -0.1700
Data Index: 2871619 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6608. Min Range: -6.6608
Max Act: 6.0670. Min Act: -0.1700
Data Index: 601504 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6608. Min Range: -6.6608
Max Act: 6.0670. Min Act: -0.1700
Data Index: 8469863 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6608. Min Range: -6.6608
Max Act: 6.0358. Min Act: -0.1700
Data Index: 3549249 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6608. Min Range: -6.6608
Max Act: 6.0358. Min Act: -0.1700
Data Index: 2112446 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6608. Min Range: -6.6608
Max Act: 6.0045. Min Act: -0.1700
Data Index: 8532403 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6608. Min Range: -6.6608
Max Act: 5.9733. Min Act: -0.1700
Data Index: 5447487 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6608. Min Range: -6.6608
Max Act: 5.9733. Min Act: -0.1700
Data Index: 4488841 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6608. Min Range: -6.6608
Max Act: 5.9420. Min Act: -0.1700
Data Index: 8814870 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6608. Min Range: -6.6608
Max Act: 5.9420. Min Act: -0.1700
Data Index: 4663199 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6608. Min Range: -6.6608
Max Act: 5.9108. Min Act: -0.1700
Data Index: 4868212 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6608. Min Range: -6.6608
Max Act: 5.9420. Min Act: -0.1700
Data Index: 806784 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6608. Min Range: -6.6608
Max Act: 5.8795. Min Act: -0.1700
Data Index: 857463 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6608. Min Range: -6.6608
Max Act: 5.8795. Min Act: -0.1700
Data Index: 6464286 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19