Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2069 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0389. Min Range: -5.0389
Max Act: 5.0389. Min Act: -0.1700
Data Index: 2130165 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.9764. Min Act: -0.1700
Data Index: 3694374 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.9139. Min Act: -0.1700
Data Index: 6088850 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.8201. Min Act: -0.1700
Data Index: 7812126 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.8201. Min Act: -0.1700
Data Index: 8492460 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.7576. Min Act: -0.1700
Data Index: 161556 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.7576. Min Act: -0.1700
Data Index: 1123041 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.7889. Min Act: -0.1700
Data Index: 3188436 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.7576. Min Act: -0.1700
Data Index: 6359476 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.7576. Min Act: -0.1700
Data Index: 6421766 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.7576. Min Act: -0.1700
Data Index: 1885539 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.7264. Min Act: -0.1700
Data Index: 6618593 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.7264. Min Act: -0.1700
Data Index: 5133015 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.7264. Min Act: -0.1700
Data Index: 1223269 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.7264. Min Act: -0.1700
Data Index: 8707358 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.7264. Min Act: -0.1700
Data Index: 2147927 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.7264. Min Act: -0.1700
Data Index: 5138413 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.7576. Min Act: -0.1700
Data Index: 143135 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.6951. Min Act: -0.1700
Data Index: 5047032 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0389. Min Range: -5.0389
Max Act: 4.6639. Min Act: -0.1700
Data Index: 5026264 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19