Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1670 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3121. Min Range: -5.3121
Max Act: 5.3121. Min Act: -0.1700
Data Index: 3867922 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3121. Min Range: -5.3121
Max Act: 5.1871. Min Act: -0.1700
Data Index: 4506637 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3121. Min Range: -5.3121
Max Act: 5.1871. Min Act: -0.1700
Data Index: 1840959 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3121. Min Range: -5.3121
Max Act: 5.1559. Min Act: -0.1700
Data Index: 6070080 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3121. Min Range: -5.3121
Max Act: 5.1246. Min Act: -0.1700
Data Index: 5130683 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3121. Min Range: -5.3121
Max Act: 5.1246. Min Act: -0.1700
Data Index: 2751033 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3121. Min Range: -5.3121
Max Act: 5.0934. Min Act: -0.1700
Data Index: 3137480 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3121. Min Range: -5.3121
Max Act: 5.0621. Min Act: -0.1700
Data Index: 4157145 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3121. Min Range: -5.3121
Max Act: 5.0621. Min Act: -0.1700
Data Index: 8717695 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3121. Min Range: -5.3121
Max Act: 4.9684. Min Act: -0.1700
Data Index: 695336 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3121. Min Range: -5.3121
Max Act: 4.9684. Min Act: -0.1700
Data Index: 3268416 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3121. Min Range: -5.3121
Max Act: 4.9684. Min Act: -0.1700
Data Index: 8820010 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3121. Min Range: -5.3121
Max Act: 4.9371. Min Act: -0.1700
Data Index: 1557899 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3121. Min Range: -5.3121
Max Act: 4.9371. Min Act: -0.1700
Data Index: 3601564 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3121. Min Range: -5.3121
Max Act: 4.9371. Min Act: -0.1700
Data Index: 6234408 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3121. Min Range: -5.3121
Max Act: 4.9059. Min Act: -0.1700
Data Index: 2682452 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3121. Min Range: -5.3121
Max Act: 4.8746. Min Act: -0.1700
Data Index: 5493147 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3121. Min Range: -5.3121
Max Act: 4.9059. Min Act: -0.1700
Data Index: 3364907 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3121. Min Range: -5.3121
Max Act: 4.9059. Min Act: -0.1700
Data Index: 8643576 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3121. Min Range: -5.3121
Max Act: 4.8434. Min Act: -0.1700
Data Index: 5636395 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19