Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3588 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0601. Min Range: -3.0601
Max Act: 3.0601. Min Act: -0.1700
Data Index: 1407863 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0601. Min Range: -3.0601
Max Act: 3.0443. Min Act: -0.1700
Data Index: 2616885 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0601. Min Range: -3.0601
Max Act: 3.0601. Min Act: -0.1700
Data Index: 4451531 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0601. Min Range: -3.0601
Max Act: 3.0443. Min Act: -0.1700
Data Index: 397391 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0601. Min Range: -3.0601
Max Act: 3.0285. Min Act: -0.1700
Data Index: 8166491 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0601. Min Range: -3.0601
Max Act: 3.0285. Min Act: -0.1700
Data Index: 1851696 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0601. Min Range: -3.0601
Max Act: 3.0443. Min Act: -0.1700
Data Index: 3603644 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0601. Min Range: -3.0601
Max Act: 2.9811. Min Act: -0.1700
Data Index: 3850777 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0601. Min Range: -3.0601
Max Act: 2.9969. Min Act: -0.1700
Data Index: 1859913 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0601. Min Range: -3.0601
Max Act: 2.9969. Min Act: -0.1700
Data Index: 1737549 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0601. Min Range: -3.0601
Max Act: 2.9969. Min Act: -0.1700
Data Index: 6985837 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0601. Min Range: -3.0601
Max Act: 2.9811. Min Act: -0.1700
Data Index: 485993 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0601. Min Range: -3.0601
Max Act: 2.9653. Min Act: -0.1700
Data Index: 1318392 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0601. Min Range: -3.0601
Max Act: 3.0127. Min Act: -0.1700
Data Index: 5028858 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0601. Min Range: -3.0601
Max Act: 2.9653. Min Act: -0.1700
Data Index: 4980778 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0601. Min Range: -3.0601
Max Act: 2.9653. Min Act: -0.1700
Data Index: 7536634 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0601. Min Range: -3.0601
Max Act: 2.9811. Min Act: -0.1700
Data Index: 1744665 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0601. Min Range: -3.0601
Max Act: 2.9495. Min Act: -0.1700
Data Index: 128580 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0601. Min Range: -3.0601
Max Act: 2.9653. Min Act: -0.1700
Data Index: 5387375 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0601. Min Range: -3.0601
Max Act: 2.9653. Min Act: -0.1700
Data Index: 6368373 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19