Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 478 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8795. Min Range: -3.8795
Max Act: 3.8795. Min Act: -0.1700
Data Index: 5224676 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8795. Min Range: -3.8795
Max Act: 3.8482. Min Act: -0.1700
Data Index: 5617181 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8795. Min Range: -3.8795
Max Act: 3.7388. Min Act: -0.1700
Data Index: 398522 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8795. Min Range: -3.8795
Max Act: 3.6292. Min Act: -0.1700
Data Index: 6365656 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8795. Min Range: -3.8795
Max Act: 3.6449. Min Act: -0.1700
Data Index: 3629584 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8795. Min Range: -3.8795
Max Act: 3.6449. Min Act: -0.1700
Data Index: 6988814 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8795. Min Range: -3.8795
Max Act: 3.6605. Min Act: -0.1700
Data Index: 1298164 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8795. Min Range: -3.8795
Max Act: 3.6292. Min Act: -0.1700
Data Index: 4391229 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8795. Min Range: -3.8795
Max Act: 3.6292. Min Act: -0.1700
Data Index: 5944395 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8795. Min Range: -3.8795
Max Act: 3.5979. Min Act: -0.1700
Data Index: 6016006 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8795. Min Range: -3.8795
Max Act: 3.5823. Min Act: -0.1700
Data Index: 7551557 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8795. Min Range: -3.8795
Max Act: 3.5040. Min Act: -0.1700
Data Index: 3369112 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8795. Min Range: -3.8795
Max Act: 3.5823. Min Act: -0.1700
Data Index: 910542 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8795. Min Range: -3.8795
Max Act: 3.5666. Min Act: -0.1700
Data Index: 3139272 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8795. Min Range: -3.8795
Max Act: 3.5666. Min Act: -0.1700
Data Index: 987592 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8795. Min Range: -3.8795
Max Act: 3.5510. Min Act: -0.1700
Data Index: 2830648 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8795. Min Range: -3.8795
Max Act: 3.5666. Min Act: -0.1700
Data Index: 662194 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8795. Min Range: -3.8795
Max Act: 3.5666. Min Act: -0.1700
Data Index: 5231304 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8795. Min Range: -3.8795
Max Act: 3.5979. Min Act: -0.1700
Data Index: 368514 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8795. Min Range: -3.8795
Max Act: 3.5353. Min Act: -0.1700
Data Index: 4476418 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19