Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2773 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.9357. Min Range: -8.9357
Max Act: 8.9357. Min Act: -0.1700
Data Index: 8787906 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9357. Min Range: -8.9357
Max Act: 8.6857. Min Act: -0.1700
Data Index: 2841510 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9357. Min Range: -8.9357
Max Act: 8.6857. Min Act: -0.1700
Data Index: 6740577 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9357. Min Range: -8.9357
Max Act: 8.5607. Min Act: -0.1700
Data Index: 4651581 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9357. Min Range: -8.9357
Max Act: 8.5607. Min Act: -0.1700
Data Index: 6979632 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9357. Min Range: -8.9357
Max Act: 8.4670. Min Act: -0.1700
Data Index: 3177715 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9357. Min Range: -8.9357
Max Act: 8.4357. Min Act: -0.1700
Data Index: 120866 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9357. Min Range: -8.9357
Max Act: 8.4045. Min Act: -0.1700
Data Index: 2470961 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9357. Min Range: -8.9357
Max Act: 8.3732. Min Act: -0.1700
Data Index: 2593899 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9357. Min Range: -8.9357
Max Act: 8.4045. Min Act: -0.1700
Data Index: 7846292 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9357. Min Range: -8.9357
Max Act: 8.3420. Min Act: -0.1700
Data Index: 5596343 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9357. Min Range: -8.9357
Max Act: 8.2795. Min Act: -0.1700
Data Index: 4843833 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9357. Min Range: -8.9357
Max Act: 8.2482. Min Act: -0.1700
Data Index: 2621883 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9357. Min Range: -8.9357
Max Act: 8.2170. Min Act: -0.1700
Data Index: 6201380 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9357. Min Range: -8.9357
Max Act: 8.2482. Min Act: -0.1700
Data Index: 6903177 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9357. Min Range: -8.9357
Max Act: 8.1857. Min Act: -0.1700
Data Index: 5944176 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9357. Min Range: -8.9357
Max Act: 8.1545. Min Act: -0.1700
Data Index: 7922387 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9357. Min Range: -8.9357
Max Act: 8.1232. Min Act: -0.1700
Data Index: 6906370 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9357. Min Range: -8.9357
Max Act: 8.1232. Min Act: -0.1700
Data Index: 3230299 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9357. Min Range: -8.9357
Max Act: 8.0920. Min Act: -0.1700
Data Index: 3576905 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19