Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3611 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.6186. Min Act: -0.1700
Data Index: 4696292 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.4936. Min Act: -0.1700
Data Index: 4797873 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.4311. Min Act: -0.1700
Data Index: 5115387 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.3998. Min Act: -0.1700
Data Index: 8303875 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.3998. Min Act: -0.1700
Data Index: 3550084 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.3686. Min Act: -0.1700
Data Index: 4660099 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.3686. Min Act: -0.1700
Data Index: 4244430 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.3686. Min Act: -0.1700
Data Index: 4797869 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.3373. Min Act: -0.1700
Data Index: 782125 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.3373. Min Act: -0.1700
Data Index: 7145321 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.3061. Min Act: -0.1700
Data Index: 4144559 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.3061. Min Act: -0.1700
Data Index: 6511848 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.3061. Min Act: -0.1700
Data Index: 2474364 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.3061. Min Act: -0.1700
Data Index: 2414521 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.3061. Min Act: -0.1700
Data Index: 410203 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.2436. Min Act: -0.1700
Data Index: 399508 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.2748. Min Act: -0.1700
Data Index: 1355604 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.2436. Min Act: -0.1700
Data Index: 2505715 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.2436. Min Act: -0.1700
Data Index: 3565554 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6186. Min Range: -4.6186
Max Act: 4.2436. Min Act: -0.1700
Data Index: 6553278 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19