Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4186 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7467. Min Range: -8.7467
Max Act: 8.7467. Min Act: -0.1700
Data Index: 362174 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7467. Min Range: -8.7467
Max Act: 8.5592. Min Act: -0.1700
Data Index: 3488826 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7467. Min Range: -8.7467
Max Act: 8.4967. Min Act: -0.1700
Data Index: 231966 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7467. Min Range: -8.7467
Max Act: 8.4342. Min Act: -0.1700
Data Index: 6801905 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7467. Min Range: -8.7467
Max Act: 8.3092. Min Act: -0.1700
Data Index: 4291302 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7467. Min Range: -8.7467
Max Act: 8.2467. Min Act: -0.1700
Data Index: 874380 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7467. Min Range: -8.7467
Max Act: 8.1842. Min Act: -0.1700
Data Index: 7619864 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7467. Min Range: -8.7467
Max Act: 8.1842. Min Act: -0.1700
Data Index: 874381 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7467. Min Range: -8.7467
Max Act: 8.0592. Min Act: -0.1700
Data Index: 7518272 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7467. Min Range: -8.7467
Max Act: 8.0592. Min Act: -0.1700
Data Index: 2902392 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7467. Min Range: -8.7467
Max Act: 7.9967. Min Act: -0.1700
Data Index: 8332560 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7467. Min Range: -8.7467
Max Act: 7.9342. Min Act: -0.1700
Data Index: 767642 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7467. Min Range: -8.7467
Max Act: 7.9342. Min Act: -0.1700
Data Index: 1210723 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7467. Min Range: -8.7467
Max Act: 7.9342. Min Act: -0.1700
Data Index: 231967 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7467. Min Range: -8.7467
Max Act: 7.9342. Min Act: -0.1700
Data Index: 4834561 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7467. Min Range: -8.7467
Max Act: 7.9342. Min Act: -0.1700
Data Index: 7044723 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7467. Min Range: -8.7467
Max Act: 7.9342. Min Act: -0.1700
Data Index: 3366144 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7467. Min Range: -8.7467
Max Act: 7.8717. Min Act: -0.1700
Data Index: 3616258 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7467. Min Range: -8.7467
Max Act: 7.8717. Min Act: -0.1700
Data Index: 7329158 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7467. Min Range: -8.7467
Max Act: 7.8717. Min Act: -0.1700
Data Index: 2602867 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19