Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4431 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0927. Min Range: -7.0927
Max Act: 7.0927. Min Act: -0.1700
Data Index: 3883059 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0927. Min Range: -7.0927
Max Act: 6.9989. Min Act: -0.1700
Data Index: 4058392 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0927. Min Range: -7.0927
Max Act: 6.7177. Min Act: -0.1700
Data Index: 740438 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0927. Min Range: -7.0927
Max Act: 6.6864. Min Act: -0.1700
Data Index: 6186635 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0927. Min Range: -7.0927
Max Act: 6.6552. Min Act: -0.1700
Data Index: 5599536 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0927. Min Range: -7.0927
Max Act: 6.5927. Min Act: -0.1700
Data Index: 3547033 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0927. Min Range: -7.0927
Max Act: 6.5614. Min Act: -0.1700
Data Index: 4511946 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0927. Min Range: -7.0927
Max Act: 6.4989. Min Act: -0.1700
Data Index: 1748858 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0927. Min Range: -7.0927
Max Act: 6.4989. Min Act: -0.1700
Data Index: 753108 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0927. Min Range: -7.0927
Max Act: 6.5302. Min Act: -0.1700
Data Index: 2462866 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0927. Min Range: -7.0927
Max Act: 6.4677. Min Act: -0.1700
Data Index: 6009705 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0927. Min Range: -7.0927
Max Act: 6.4677. Min Act: -0.1700
Data Index: 4819275 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0927. Min Range: -7.0927
Max Act: 6.4677. Min Act: -0.1700
Data Index: 7790805 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0927. Min Range: -7.0927
Max Act: 6.4364. Min Act: -0.1700
Data Index: 4805135 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0927. Min Range: -7.0927
Max Act: 6.4052. Min Act: -0.1700
Data Index: 8162791 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0927. Min Range: -7.0927
Max Act: 6.4052. Min Act: -0.1700
Data Index: 3172895 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0927. Min Range: -7.0927
Max Act: 6.3427. Min Act: -0.1700
Data Index: 3519375 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0927. Min Range: -7.0927
Max Act: 6.3427. Min Act: -0.1700
Data Index: 4834399 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0927. Min Range: -7.0927
Max Act: 6.3427. Min Act: -0.1700
Data Index: 3983159 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0927. Min Range: -7.0927
Max Act: 6.3739. Min Act: -0.1700
Data Index: 4337691 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19