Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 928 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4563. Min Range: -6.4563
Max Act: 6.4563. Min Act: -0.1700
Data Index: 3723662 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4563. Min Range: -6.4563
Max Act: 6.3938. Min Act: -0.1700
Data Index: 6362409 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4563. Min Range: -6.4563
Max Act: 6.3938. Min Act: -0.1700
Data Index: 1057219 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4563. Min Range: -6.4563
Max Act: 6.1751. Min Act: -0.1700
Data Index: 5121749 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4563. Min Range: -6.4563
Max Act: 6.2063. Min Act: -0.1700
Data Index: 6057331 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4563. Min Range: -6.4563
Max Act: 6.2063. Min Act: -0.1700
Data Index: 4051603 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4563. Min Range: -6.4563
Max Act: 6.1751. Min Act: -0.1700
Data Index: 2511416 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4563. Min Range: -6.4563
Max Act: 6.1751. Min Act: -0.1700
Data Index: 559722 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4563. Min Range: -6.4563
Max Act: 6.1438. Min Act: -0.1700
Data Index: 1958913 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4563. Min Range: -6.4563
Max Act: 6.0813. Min Act: -0.1700
Data Index: 885618 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4563. Min Range: -6.4563
Max Act: 6.0813. Min Act: -0.1700
Data Index: 6934428 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4563. Min Range: -6.4563
Max Act: 6.0813. Min Act: -0.1700
Data Index: 869182 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4563. Min Range: -6.4563
Max Act: 6.0813. Min Act: -0.1700
Data Index: 2861515 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4563. Min Range: -6.4563
Max Act: 6.0501. Min Act: -0.1700
Data Index: 2899723 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4563. Min Range: -6.4563
Max Act: 5.9876. Min Act: -0.1700
Data Index: 7231372 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4563. Min Range: -6.4563
Max Act: 5.9876. Min Act: -0.1700
Data Index: 5316767 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4563. Min Range: -6.4563
Max Act: 6.0501. Min Act: -0.1700
Data Index: 2356564 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4563. Min Range: -6.4563
Max Act: 5.9876. Min Act: -0.1700
Data Index: 4026402 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4563. Min Range: -6.4563
Max Act: 5.9876. Min Act: -0.1700
Data Index: 7971886 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4563. Min Range: -6.4563
Max Act: 5.9876. Min Act: -0.1700
Data Index: 4246243 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19