Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 693 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6177. Min Range: -5.6177
Max Act: 5.6177. Min Act: -0.1700
Data Index: 2014219 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6177. Min Range: -5.6177
Max Act: 5.5240. Min Act: -0.1700
Data Index: 137555 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6177. Min Range: -5.6177
Max Act: 5.5240. Min Act: -0.1700
Data Index: 1826387 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6177. Min Range: -5.6177
Max Act: 5.4927. Min Act: -0.1700
Data Index: 1872218 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6177. Min Range: -5.6177
Max Act: 5.4927. Min Act: -0.1700
Data Index: 505196 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6177. Min Range: -5.6177
Max Act: 5.4927. Min Act: -0.1700
Data Index: 3588094 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6177. Min Range: -5.6177
Max Act: 5.4615. Min Act: -0.1700
Data Index: 1886533 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6177. Min Range: -5.6177
Max Act: 5.4615. Min Act: -0.1700
Data Index: 3878985 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6177. Min Range: -5.6177
Max Act: 5.4615. Min Act: -0.1700
Data Index: 1862276 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6177. Min Range: -5.6177
Max Act: 5.4615. Min Act: -0.1700
Data Index: 5360719 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6177. Min Range: -5.6177
Max Act: 5.4615. Min Act: -0.1700
Data Index: 1385738 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6177. Min Range: -5.6177
Max Act: 5.4615. Min Act: -0.1700
Data Index: 1488424 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6177. Min Range: -5.6177
Max Act: 5.4615. Min Act: -0.1700
Data Index: 7509720 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6177. Min Range: -5.6177
Max Act: 5.4615. Min Act: -0.1700
Data Index: 6534100 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6177. Min Range: -5.6177
Max Act: 5.4302. Min Act: -0.1700
Data Index: 3140566 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6177. Min Range: -5.6177
Max Act: 5.4302. Min Act: -0.1700
Data Index: 7046713 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6177. Min Range: -5.6177
Max Act: 5.4302. Min Act: -0.1700
Data Index: 4634221 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6177. Min Range: -5.6177
Max Act: 5.3990. Min Act: -0.1700
Data Index: 3645861 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6177. Min Range: -5.6177
Max Act: 5.4302. Min Act: -0.1700
Data Index: 3225470 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6177. Min Range: -5.6177
Max Act: 5.4302. Min Act: -0.1700
Data Index: 3753830 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19