Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3620 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.6354. Min Range: -11.6354
Max Act: 11.6354. Min Act: -0.1700
Data Index: 7066297 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.6354. Min Range: -11.6354
Max Act: 11.1354. Min Act: -0.1700
Data Index: 7675184 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.6354. Min Range: -11.6354
Max Act: 10.9479. Min Act: -0.1700
Data Index: 883556 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.6354. Min Range: -11.6354
Max Act: 10.9479. Min Act: -0.1700
Data Index: 8159918 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.6354. Min Range: -11.6354
Max Act: 10.9479. Min Act: -0.1700
Data Index: 7397007 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.6354. Min Range: -11.6354
Max Act: 10.8854. Min Act: -0.1700
Data Index: 7165481 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.6354. Min Range: -11.6354
Max Act: 10.8229. Min Act: -0.1700
Data Index: 5713683 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.6354. Min Range: -11.6354
Max Act: 10.7604. Min Act: -0.1700
Data Index: 321866 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.6354. Min Range: -11.6354
Max Act: 10.7604. Min Act: -0.1700
Data Index: 5290939 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.6354. Min Range: -11.6354
Max Act: 10.7604. Min Act: -0.1700
Data Index: 2105662 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.6354. Min Range: -11.6354
Max Act: 10.7604. Min Act: -0.1700
Data Index: 7543114 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.6354. Min Range: -11.6354
Max Act: 10.6979. Min Act: -0.1700
Data Index: 2744512 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.6354. Min Range: -11.6354
Max Act: 10.6354. Min Act: -0.1700
Data Index: 2190330 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.6354. Min Range: -11.6354
Max Act: 10.6354. Min Act: -0.1700
Data Index: 6586470 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.6354. Min Range: -11.6354
Max Act: 10.6354. Min Act: -0.1700
Data Index: 295062 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.6354. Min Range: -11.6354
Max Act: 10.6354. Min Act: -0.1700
Data Index: 1875073 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.6354. Min Range: -11.6354
Max Act: 10.6354. Min Act: -0.1700
Data Index: 4777463 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.6354. Min Range: -11.6354
Max Act: 10.6354. Min Act: -0.1700
Data Index: 4083434 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.6354. Min Range: -11.6354
Max Act: 10.5104. Min Act: -0.1700
Data Index: 7011035 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.6354. Min Range: -11.6354
Max Act: 10.5104. Min Act: -0.1700
Data Index: 6010914 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19