Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 342 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8502. Min Range: -6.8502
Max Act: 6.8502. Min Act: -0.1700
Data Index: 5358415 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8502. Min Range: -6.8502
Max Act: 6.4439. Min Act: -0.1700
Data Index: 2864479 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8502. Min Range: -6.8502
Max Act: 6.3814. Min Act: -0.1700
Data Index: 8102932 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8502. Min Range: -6.8502
Max Act: 6.3502. Min Act: -0.1700
Data Index: 8546499 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8502. Min Range: -6.8502
Max Act: 6.3189. Min Act: -0.1700
Data Index: 7132386 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8502. Min Range: -6.8502
Max Act: 6.2877. Min Act: -0.1700
Data Index: 1842379 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8502. Min Range: -6.8502
Max Act: 6.2564. Min Act: -0.1700
Data Index: 8786893 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8502. Min Range: -6.8502
Max Act: 6.2564. Min Act: -0.1700
Data Index: 3559090 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8502. Min Range: -6.8502
Max Act: 6.2564. Min Act: -0.1700
Data Index: 7143807 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8502. Min Range: -6.8502
Max Act: 6.2877. Min Act: -0.1700
Data Index: 797173 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8502. Min Range: -6.8502
Max Act: 6.2877. Min Act: -0.1700
Data Index: 5255613 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8502. Min Range: -6.8502
Max Act: 6.2252. Min Act: -0.1700
Data Index: 6016430 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8502. Min Range: -6.8502
Max Act: 6.2252. Min Act: -0.1700
Data Index: 4723288 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8502. Min Range: -6.8502
Max Act: 6.1627. Min Act: -0.1700
Data Index: 8348695 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8502. Min Range: -6.8502
Max Act: 6.1627. Min Act: -0.1700
Data Index: 122523 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8502. Min Range: -6.8502
Max Act: 6.1939. Min Act: -0.1700
Data Index: 6182119 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8502. Min Range: -6.8502
Max Act: 6.1627. Min Act: -0.1700
Data Index: 2853740 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8502. Min Range: -6.8502
Max Act: 6.1314. Min Act: -0.1700
Data Index: 2622855 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8502. Min Range: -6.8502
Max Act: 6.1627. Min Act: -0.1700
Data Index: 5242791 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8502. Min Range: -6.8502
Max Act: 6.1314. Min Act: -0.1700
Data Index: 355656 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19