Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2003 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2102. Min Range: -8.2102
Max Act: 8.2102. Min Act: -0.1700
Data Index: 8748468 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2102. Min Range: -8.2102
Max Act: 8.1477. Min Act: -0.1700
Data Index: 5499234 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2102. Min Range: -8.2102
Max Act: 8.0852. Min Act: -0.1700
Data Index: 2114347 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2102. Min Range: -8.2102
Max Act: 8.0852. Min Act: -0.1700
Data Index: 2438156 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2102. Min Range: -8.2102
Max Act: 8.0227. Min Act: -0.1700
Data Index: 2241034 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.9602. Min Act: -0.1700
Data Index: 2791253 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.9602. Min Act: -0.1700
Data Index: 12825 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.8977. Min Act: -0.1700
Data Index: 232048 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.8977. Min Act: -0.1700
Data Index: 7058994 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.8352. Min Act: -0.1700
Data Index: 1212941 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.8352. Min Act: -0.1700
Data Index: 2193085 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.8352. Min Act: -0.1700
Data Index: 7526691 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.8977. Min Act: -0.1700
Data Index: 4371056 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.8352. Min Act: -0.1700
Data Index: 6231933 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.8352. Min Act: -0.1700
Data Index: 1076176 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.7727. Min Act: -0.1700
Data Index: 6879531 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.7102. Min Act: -0.1700
Data Index: 8443053 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.7727. Min Act: -0.1700
Data Index: 4792910 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.7727. Min Act: -0.1700
Data Index: 4627374 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2102. Min Range: -8.2102
Max Act: 7.7102. Min Act: -0.1700
Data Index: 2499475 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19