Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3425 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.9034. Min Range: -12.9034
Max Act: 12.9034. Min Act: -0.1700
Data Index: 5597796 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.9034. Min Range: -12.9034
Max Act: 12.6534. Min Act: -0.1700
Data Index: 7107099 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.9034. Min Range: -12.9034
Max Act: 12.6534. Min Act: -0.1700
Data Index: 8530926 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.9034. Min Range: -12.9034
Max Act: 12.6534. Min Act: -0.1700
Data Index: 7430870 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.9034. Min Range: -12.9034
Max Act: 12.5284. Min Act: -0.1700
Data Index: 4945954 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.9034. Min Range: -12.9034
Max Act: 12.5284. Min Act: -0.1700
Data Index: 7145883 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.9034. Min Range: -12.9034
Max Act: 12.5284. Min Act: -0.1700
Data Index: 7430868 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.9034. Min Range: -12.9034
Max Act: 12.4659. Min Act: -0.1700
Data Index: 6099901 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.9034. Min Range: -12.9034
Max Act: 12.4034. Min Act: -0.1700
Data Index: 2272738 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.9034. Min Range: -12.9034
Max Act: 12.4034. Min Act: -0.1700
Data Index: 7936689 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.9034. Min Range: -12.9034
Max Act: 12.4659. Min Act: -0.1700
Data Index: 3643473 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.9034. Min Range: -12.9034
Max Act: 12.2784. Min Act: -0.1700
Data Index: 4233851 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.9034. Min Range: -12.9034
Max Act: 12.2159. Min Act: -0.1700
Data Index: 6970852 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.9034. Min Range: -12.9034
Max Act: 12.1534. Min Act: -0.1700
Data Index: 5490306 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.9034. Min Range: -12.9034
Max Act: 12.1534. Min Act: -0.1700
Data Index: 6109052 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.9034. Min Range: -12.9034
Max Act: 12.0909. Min Act: -0.1700
Data Index: 590704 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.9034. Min Range: -12.9034
Max Act: 12.0909. Min Act: -0.1700
Data Index: 3327609 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.9034. Min Range: -12.9034
Max Act: 12.0909. Min Act: -0.1700
Data Index: 3103769 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.9034. Min Range: -12.9034
Max Act: 12.0284. Min Act: -0.1700
Data Index: 6023444 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.9034. Min Range: -12.9034
Max Act: 12.0284. Min Act: -0.1700
Data Index: 1737303 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19