Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1326 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.7235. Min Act: -0.1700
Data Index: 7406306 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.6922. Min Act: -0.1700
Data Index: 3769331 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.6297. Min Act: -0.1700
Data Index: 3626621 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.5985. Min Act: -0.1700
Data Index: 1164650 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.5672. Min Act: -0.1700
Data Index: 5414032 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.5672. Min Act: -0.1700
Data Index: 5869996 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.5672. Min Act: -0.1700
Data Index: 6852732 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.5985. Min Act: -0.1700
Data Index: 3735378 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.5672. Min Act: -0.1700
Data Index: 1685750 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.5047. Min Act: -0.1700
Data Index: 5025752 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.5047. Min Act: -0.1700
Data Index: 5047018 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.5360. Min Act: -0.1700
Data Index: 3040480 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.5360. Min Act: -0.1700
Data Index: 7518341 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.5360. Min Act: -0.1700
Data Index: 3551794 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.5360. Min Act: -0.1700
Data Index: 5437506 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.4735. Min Act: -0.1700
Data Index: 5767626 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.5047. Min Act: -0.1700
Data Index: 3123677 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.5047. Min Act: -0.1700
Data Index: 1040589 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.5047. Min Act: -0.1700
Data Index: 4086355 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7235. Min Range: -4.7235
Max Act: 4.5047. Min Act: -0.1700
Data Index: 1006311 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19