Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 966 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.4566. Min Act: -0.1700
Data Index: 7191855 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.3629. Min Act: -0.1700
Data Index: 3111503 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.3941. Min Act: -0.1700
Data Index: 5259262 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.3629. Min Act: -0.1700
Data Index: 874385 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.3941. Min Act: -0.1700
Data Index: 2389568 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.3629. Min Act: -0.1700
Data Index: 1508462 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.3004. Min Act: -0.1700
Data Index: 3477800 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.3004. Min Act: -0.1700
Data Index: 1438700 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.3316. Min Act: -0.1700
Data Index: 4695746 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.3004. Min Act: -0.1700
Data Index: 8091921 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.2691. Min Act: -0.1700
Data Index: 5914854 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.2379. Min Act: -0.1700
Data Index: 477436 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.2379. Min Act: -0.1700
Data Index: 8736863 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.2066. Min Act: -0.1700
Data Index: 945601 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.2066. Min Act: -0.1700
Data Index: 5896767 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.1754. Min Act: -0.1700
Data Index: 5686249 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.1754. Min Act: -0.1700
Data Index: 5498534 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.1754. Min Act: -0.1700
Data Index: 6788589 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.1754. Min Act: -0.1700
Data Index: 5939717 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4566. Min Range: -5.4566
Max Act: 5.1441. Min Act: -0.1700
Data Index: 2086379 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19