Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2226 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4490. Min Range: -5.4490
Max Act: 5.4490. Min Act: -0.1700
Data Index: 4874392 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4490. Min Range: -5.4490
Max Act: 5.3865. Min Act: -0.1700
Data Index: 5328565 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4490. Min Range: -5.4490
Max Act: 5.3553. Min Act: -0.1700
Data Index: 4347944 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4490. Min Range: -5.4490
Max Act: 5.3865. Min Act: -0.1700
Data Index: 6377904 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4490. Min Range: -5.4490
Max Act: 5.3553. Min Act: -0.1700
Data Index: 1269218 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4490. Min Range: -5.4490
Max Act: 5.3553. Min Act: -0.1700
Data Index: 3132318 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4490. Min Range: -5.4490
Max Act: 5.3553. Min Act: -0.1700
Data Index: 796906 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4490. Min Range: -5.4490
Max Act: 5.3240. Min Act: -0.1700
Data Index: 3741849 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4490. Min Range: -5.4490
Max Act: 5.2928. Min Act: -0.1700
Data Index: 8684906 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4490. Min Range: -5.4490
Max Act: 5.2928. Min Act: -0.1700
Data Index: 2624723 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4490. Min Range: -5.4490
Max Act: 5.2928. Min Act: -0.1700
Data Index: 604673 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4490. Min Range: -5.4490
Max Act: 5.2928. Min Act: -0.1700
Data Index: 7599299 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4490. Min Range: -5.4490
Max Act: 5.2928. Min Act: -0.1700
Data Index: 2357296 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4490. Min Range: -5.4490
Max Act: 5.2615. Min Act: -0.1700
Data Index: 5293019 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4490. Min Range: -5.4490
Max Act: 5.2928. Min Act: -0.1700
Data Index: 7505893 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4490. Min Range: -5.4490
Max Act: 5.2615. Min Act: -0.1700
Data Index: 7262804 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4490. Min Range: -5.4490
Max Act: 5.2615. Min Act: -0.1700
Data Index: 4544561 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4490. Min Range: -5.4490
Max Act: 5.2615. Min Act: -0.1700
Data Index: 2873594 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4490. Min Range: -5.4490
Max Act: 5.2303. Min Act: -0.1700
Data Index: 7137218 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4490. Min Range: -5.4490
Max Act: 5.2615. Min Act: -0.1700
Data Index: 4088463 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19