Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3467 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3721. Min Range: -6.3721
Max Act: 6.3721. Min Act: -0.1700
Data Index: 1387596 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3721. Min Range: -6.3721
Max Act: 6.1846. Min Act: -0.1700
Data Index: 4557515 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3721. Min Range: -6.3721
Max Act: 6.1221. Min Act: -0.1700
Data Index: 961485 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3721. Min Range: -6.3721
Max Act: 6.1221. Min Act: -0.1700
Data Index: 1960630 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3721. Min Range: -6.3721
Max Act: 6.0908. Min Act: -0.1700
Data Index: 771185 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3721. Min Range: -6.3721
Max Act: 6.0908. Min Act: -0.1700
Data Index: 5816869 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3721. Min Range: -6.3721
Max Act: 6.0596. Min Act: -0.1700
Data Index: 527600 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3721. Min Range: -6.3721
Max Act: 6.0596. Min Act: -0.1700
Data Index: 2299062 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3721. Min Range: -6.3721
Max Act: 6.0283. Min Act: -0.1700
Data Index: 6679556 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3721. Min Range: -6.3721
Max Act: 6.0283. Min Act: -0.1700
Data Index: 3410973 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3721. Min Range: -6.3721
Max Act: 6.0283. Min Act: -0.1700
Data Index: 983058 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3721. Min Range: -6.3721
Max Act: 5.9971. Min Act: -0.1700
Data Index: 7022768 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3721. Min Range: -6.3721
Max Act: 5.9971. Min Act: -0.1700
Data Index: 466685 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3721. Min Range: -6.3721
Max Act: 5.9971. Min Act: -0.1700
Data Index: 1212231 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3721. Min Range: -6.3721
Max Act: 5.9971. Min Act: -0.1700
Data Index: 639075 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3721. Min Range: -6.3721
Max Act: 5.9971. Min Act: -0.1700
Data Index: 5207706 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3721. Min Range: -6.3721
Max Act: 5.9658. Min Act: -0.1700
Data Index: 8314876 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3721. Min Range: -6.3721
Max Act: 5.9346. Min Act: -0.1700
Data Index: 6392101 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3721. Min Range: -6.3721
Max Act: 5.9346. Min Act: -0.1700
Data Index: 6429887 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3721. Min Range: -6.3721
Max Act: 5.9346. Min Act: -0.1700
Data Index: 4789661 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19