Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3316 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1721. Min Range: -6.1721
Max Act: 6.1721. Min Act: -0.1700
Data Index: 7742544 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1721. Min Range: -6.1721
Max Act: 6.0784. Min Act: -0.1700
Data Index: 6258830 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1721. Min Range: -6.1721
Max Act: 6.0784. Min Act: -0.1700
Data Index: 8481180 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1721. Min Range: -6.1721
Max Act: 6.0784. Min Act: -0.1700
Data Index: 4834981 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1721. Min Range: -6.1721
Max Act: 6.0471. Min Act: -0.1700
Data Index: 6488093 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1721. Min Range: -6.1721
Max Act: 6.0471. Min Act: -0.1700
Data Index: 2555254 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1721. Min Range: -6.1721
Max Act: 5.9534. Min Act: -0.1700
Data Index: 6490704 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1721. Min Range: -6.1721
Max Act: 5.9534. Min Act: -0.1700
Data Index: 4971738 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1721. Min Range: -6.1721
Max Act: 5.9534. Min Act: -0.1700
Data Index: 2273784 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1721. Min Range: -6.1721
Max Act: 5.9534. Min Act: -0.1700
Data Index: 4671019 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1721. Min Range: -6.1721
Max Act: 5.9221. Min Act: -0.1700
Data Index: 3839529 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1721. Min Range: -6.1721
Max Act: 5.8909. Min Act: -0.1700
Data Index: 1429122 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1721. Min Range: -6.1721
Max Act: 5.8909. Min Act: -0.1700
Data Index: 5513589 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1721. Min Range: -6.1721
Max Act: 5.8909. Min Act: -0.1700
Data Index: 8566441 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1721. Min Range: -6.1721
Max Act: 5.8596. Min Act: -0.1700
Data Index: 873684 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1721. Min Range: -6.1721
Max Act: 5.8596. Min Act: -0.1700
Data Index: 2250249 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1721. Min Range: -6.1721
Max Act: 5.8596. Min Act: -0.1700
Data Index: 5623717 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1721. Min Range: -6.1721
Max Act: 5.7971. Min Act: -0.1700
Data Index: 6605408 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1721. Min Range: -6.1721
Max Act: 5.7659. Min Act: -0.1700
Data Index: 1337668 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1721. Min Range: -6.1721
Max Act: 5.7971. Min Act: -0.1700
Data Index: 4010306 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19