Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5031 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3527. Min Range: -3.3527
Max Act: 3.3527. Min Act: -0.1700
Data Index: 20770 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3527. Min Range: -3.3527
Max Act: 3.2899. Min Act: -0.1700
Data Index: 3388130 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3527. Min Range: -3.3527
Max Act: 3.1956. Min Act: -0.1700
Data Index: 5583742 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3527. Min Range: -3.3527
Max Act: 3.1956. Min Act: -0.1700
Data Index: 1984340 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3527. Min Range: -3.3527
Max Act: 3.1642. Min Act: -0.1700
Data Index: 7546736 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3527. Min Range: -3.3527
Max Act: 3.1484. Min Act: -0.1700
Data Index: 3647748 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3527. Min Range: -3.3527
Max Act: 3.1169. Min Act: -0.1700
Data Index: 7546740 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3527. Min Range: -3.3527
Max Act: 3.1327. Min Act: -0.1700
Data Index: 7546733 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3527. Min Range: -3.3527
Max Act: 3.1169. Min Act: -0.1700
Data Index: 7546734 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3527. Min Range: -3.3527
Max Act: 3.0854. Min Act: -0.1700
Data Index: 5079645 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3527. Min Range: -3.3527
Max Act: 3.0697. Min Act: -0.1700
Data Index: 7546739 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3527. Min Range: -3.3527
Max Act: 3.0381. Min Act: -0.1700
Data Index: 1959333 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3527. Min Range: -3.3527
Max Act: 3.0381. Min Act: -0.1700
Data Index: 4728324 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3527. Min Range: -3.3527
Max Act: 3.0223. Min Act: -0.1700
Data Index: 7002875 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3527. Min Range: -3.3527
Max Act: 3.0223. Min Act: -0.1700
Data Index: 4385914 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3527. Min Range: -3.3527
Max Act: 3.0223. Min Act: -0.1700
Data Index: 5116626 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3527. Min Range: -3.3527
Max Act: 3.0223. Min Act: -0.1700
Data Index: 6199794 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3527. Min Range: -3.3527
Max Act: 3.0065. Min Act: -0.1700
Data Index: 7142904 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3527. Min Range: -3.3527
Max Act: 2.9907. Min Act: -0.1700
Data Index: 3574469 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3527. Min Range: -3.3527
Max Act: 2.9749. Min Act: -0.1700
Data Index: 2865 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19