Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3677 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0796. Min Range: -7.0796
Max Act: 7.0796. Min Act: -0.1700
Data Index: 2181487 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0796. Min Range: -7.0796
Max Act: 6.4546. Min Act: -0.1700
Data Index: 7313276 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0796. Min Range: -7.0796
Max Act: 6.4546. Min Act: -0.1700
Data Index: 954744 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0796. Min Range: -7.0796
Max Act: 6.4233. Min Act: -0.1700
Data Index: 5122657 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0796. Min Range: -7.0796
Max Act: 6.4233. Min Act: -0.1700
Data Index: 2067657 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0796. Min Range: -7.0796
Max Act: 6.3921. Min Act: -0.1700
Data Index: 5362964 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0796. Min Range: -7.0796
Max Act: 6.3608. Min Act: -0.1700
Data Index: 2311275 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0796. Min Range: -7.0796
Max Act: 6.3608. Min Act: -0.1700
Data Index: 3816973 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0796. Min Range: -7.0796
Max Act: 6.2671. Min Act: -0.1700
Data Index: 7426773 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0796. Min Range: -7.0796
Max Act: 6.2358. Min Act: -0.1700
Data Index: 4134860 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0796. Min Range: -7.0796
Max Act: 6.2358. Min Act: -0.1700
Data Index: 2595554 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0796. Min Range: -7.0796
Max Act: 6.1421. Min Act: -0.1700
Data Index: 8221073 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0796. Min Range: -7.0796
Max Act: 6.1733. Min Act: -0.1700
Data Index: 5285059 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0796. Min Range: -7.0796
Max Act: 6.1733. Min Act: -0.1700
Data Index: 550591 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0796. Min Range: -7.0796
Max Act: 6.1733. Min Act: -0.1700
Data Index: 4441005 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0796. Min Range: -7.0796
Max Act: 6.1108. Min Act: -0.1700
Data Index: 1855292 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0796. Min Range: -7.0796
Max Act: 6.1108. Min Act: -0.1700
Data Index: 7495769 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0796. Min Range: -7.0796
Max Act: 6.1108. Min Act: -0.1700
Data Index: 5368722 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0796. Min Range: -7.0796
Max Act: 6.0796. Min Act: -0.1700
Data Index: 2635400 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0796. Min Range: -7.0796
Max Act: 6.0796. Min Act: -0.1700
Data Index: 7558276 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19