Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4303 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5332. Min Range: -2.5332
Max Act: 2.5332. Min Act: -0.1700
Data Index: 6133331 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5332. Min Range: -2.5332
Max Act: 2.4684. Min Act: -0.1700
Data Index: 3922695 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5332. Min Range: -2.5332
Max Act: 2.2885. Min Act: -0.1700
Data Index: 3604279 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5332. Min Range: -2.5332
Max Act: 2.2720. Min Act: -0.1700
Data Index: 7529017 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5332. Min Range: -2.5332
Max Act: 2.2885. Min Act: -0.1700
Data Index: 8675309 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5332. Min Range: -2.5332
Max Act: 2.2885. Min Act: -0.1700
Data Index: 7026536 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5332. Min Range: -2.5332
Max Act: 2.2720. Min Act: -0.1700
Data Index: 113598 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5332. Min Range: -2.5332
Max Act: 2.2555. Min Act: -0.1700
Data Index: 6764397 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5332. Min Range: -2.5332
Max Act: 2.2720. Min Act: -0.1700
Data Index: 8608819 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5332. Min Range: -2.5332
Max Act: 2.2720. Min Act: -0.1700
Data Index: 8494882 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5332. Min Range: -2.5332
Max Act: 2.2885. Min Act: -0.1700
Data Index: 7125569 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5332. Min Range: -2.5332
Max Act: 2.2390. Min Act: -0.1700
Data Index: 6004990 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5332. Min Range: -2.5332
Max Act: 2.2555. Min Act: -0.1700
Data Index: 7547460 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5332. Min Range: -2.5332
Max Act: 2.2390. Min Act: -0.1700
Data Index: 4041221 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5332. Min Range: -2.5332
Max Act: 2.2555. Min Act: -0.1700
Data Index: 5060536 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5332. Min Range: -2.5332
Max Act: 2.2555. Min Act: -0.1700
Data Index: 4487403 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5332. Min Range: -2.5332
Max Act: 2.2555. Min Act: -0.1700
Data Index: 8374824 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5332. Min Range: -2.5332
Max Act: 2.2555. Min Act: -0.1700
Data Index: 4516226 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5332. Min Range: -2.5332
Max Act: 2.2555. Min Act: -0.1700
Data Index: 4699495 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5332. Min Range: -2.5332
Max Act: 2.2390. Min Act: -0.1700
Data Index: 7571784 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19