Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 921 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4355. Min Range: -4.4355
Max Act: 4.4355. Min Act: -0.1700
Data Index: 680810 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4355. Min Range: -4.4355
Max Act: 4.3730. Min Act: -0.1700
Data Index: 5821626 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4355. Min Range: -4.4355
Max Act: 4.3417. Min Act: -0.1700
Data Index: 4709127 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4355. Min Range: -4.4355
Max Act: 4.3417. Min Act: -0.1700
Data Index: 774960 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4355. Min Range: -4.4355
Max Act: 4.3105. Min Act: -0.1700
Data Index: 7988610 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4355. Min Range: -4.4355
Max Act: 4.2792. Min Act: -0.1700
Data Index: 923646 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4355. Min Range: -4.4355
Max Act: 4.2480. Min Act: -0.1700
Data Index: 3138638 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4355. Min Range: -4.4355
Max Act: 4.2480. Min Act: -0.1700
Data Index: 7172944 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4355. Min Range: -4.4355
Max Act: 4.2480. Min Act: -0.1700
Data Index: 774959 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4355. Min Range: -4.4355
Max Act: 4.2167. Min Act: -0.1700
Data Index: 1577857 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4355. Min Range: -4.4355
Max Act: 4.2480. Min Act: -0.1700
Data Index: 2132787 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4355. Min Range: -4.4355
Max Act: 4.2480. Min Act: -0.1700
Data Index: 2330122 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4355. Min Range: -4.4355
Max Act: 4.2480. Min Act: -0.1700
Data Index: 4759975 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4355. Min Range: -4.4355
Max Act: 4.2480. Min Act: -0.1700
Data Index: 8436360 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4355. Min Range: -4.4355
Max Act: 4.2167. Min Act: -0.1700
Data Index: 6720953 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4355. Min Range: -4.4355
Max Act: 4.2167. Min Act: -0.1700
Data Index: 1131272 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4355. Min Range: -4.4355
Max Act: 4.2167. Min Act: -0.1700
Data Index: 3811202 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4355. Min Range: -4.4355
Max Act: 4.2167. Min Act: -0.1700
Data Index: 3816991 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4355. Min Range: -4.4355
Max Act: 4.1855. Min Act: -0.1700
Data Index: 977374 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4355. Min Range: -4.4355
Max Act: 4.1855. Min Act: -0.1700
Data Index: 1887642 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19