Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1297 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9246. Min Range: -7.9246
Max Act: 7.9246. Min Act: -0.1700
Data Index: 126193 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9246. Min Range: -7.9246
Max Act: 7.5496. Min Act: -0.1700
Data Index: 1000388 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9246. Min Range: -7.9246
Max Act: 7.4246. Min Act: -0.1700
Data Index: 3879583 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9246. Min Range: -7.9246
Max Act: 7.3621. Min Act: -0.1700
Data Index: 6437684 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9246. Min Range: -7.9246
Max Act: 7.3308. Min Act: -0.1700
Data Index: 3363731 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9246. Min Range: -7.9246
Max Act: 7.2996. Min Act: -0.1700
Data Index: 6741256 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9246. Min Range: -7.9246
Max Act: 7.2996. Min Act: -0.1700
Data Index: 6532972 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9246. Min Range: -7.9246
Max Act: 7.2371. Min Act: -0.1700
Data Index: 6030200 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9246. Min Range: -7.9246
Max Act: 7.2371. Min Act: -0.1700
Data Index: 1359494 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9246. Min Range: -7.9246
Max Act: 7.2371. Min Act: -0.1700
Data Index: 1539404 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9246. Min Range: -7.9246
Max Act: 7.2058. Min Act: -0.1700
Data Index: 5852010 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9246. Min Range: -7.9246
Max Act: 7.1433. Min Act: -0.1700
Data Index: 5382934 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9246. Min Range: -7.9246
Max Act: 7.1121. Min Act: -0.1700
Data Index: 3863990 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9246. Min Range: -7.9246
Max Act: 7.0496. Min Act: -0.1700
Data Index: 5562444 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9246. Min Range: -7.9246
Max Act: 7.1121. Min Act: -0.1700
Data Index: 8299241 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9246. Min Range: -7.9246
Max Act: 7.0183. Min Act: -0.1700
Data Index: 5785948 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9246. Min Range: -7.9246
Max Act: 7.0496. Min Act: -0.1700
Data Index: 1194769 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9246. Min Range: -7.9246
Max Act: 7.0496. Min Act: -0.1700
Data Index: 7752931 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9246. Min Range: -7.9246
Max Act: 7.0496. Min Act: -0.1700
Data Index: 4152584 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9246. Min Range: -7.9246
Max Act: 7.0183. Min Act: -0.1700
Data Index: 2111874 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19