Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4009 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0659. Min Range: -5.0659
Max Act: 5.0659. Min Act: -0.1700
Data Index: 4408455 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0659. Min Range: -5.0659
Max Act: 4.0659. Min Act: -0.1700
Data Index: 3119396 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0659. Min Range: -5.0659
Max Act: 4.0346. Min Act: -0.1700
Data Index: 7794923 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0659. Min Range: -5.0659
Max Act: 4.0033. Min Act: -0.1700
Data Index: 4144509 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0659. Min Range: -5.0659
Max Act: 4.0346. Min Act: -0.1700
Data Index: 4780570 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0659. Min Range: -5.0659
Max Act: 3.9721. Min Act: -0.1700
Data Index: 1191386 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0659. Min Range: -5.0659
Max Act: 3.9408. Min Act: -0.1700
Data Index: 8237559 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0659. Min Range: -5.0659
Max Act: 3.9408. Min Act: -0.1700
Data Index: 4353533 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0659. Min Range: -5.0659
Max Act: 3.9095. Min Act: -0.1700
Data Index: 7041566 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0659. Min Range: -5.0659
Max Act: 3.8783. Min Act: -0.1700
Data Index: 5474531 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0659. Min Range: -5.0659
Max Act: 3.8783. Min Act: -0.1700
Data Index: 2748285 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0659. Min Range: -5.0659
Max Act: 3.8470. Min Act: -0.1700
Data Index: 5495887 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0659. Min Range: -5.0659
Max Act: 3.8470. Min Act: -0.1700
Data Index: 475082 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0659. Min Range: -5.0659
Max Act: 3.8470. Min Act: -0.1700
Data Index: 6428037 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0659. Min Range: -5.0659
Max Act: 3.8470. Min Act: -0.1700
Data Index: 1374037 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0659. Min Range: -5.0659
Max Act: 3.8470. Min Act: -0.1700
Data Index: 1581687 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0659. Min Range: -5.0659
Max Act: 3.8157. Min Act: -0.1700
Data Index: 1015806 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0659. Min Range: -5.0659
Max Act: 3.8470. Min Act: -0.1700
Data Index: 3337874 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0659. Min Range: -5.0659
Max Act: 3.8783. Min Act: -0.1700
Data Index: 7254269 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0659. Min Range: -5.0659
Max Act: 3.8157. Min Act: -0.1700
Data Index: 1045237 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19