Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3690 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5412. Min Range: -6.5412
Max Act: 6.5412. Min Act: -0.1700
Data Index: 7597162 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5412. Min Range: -6.5412
Max Act: 6.4162. Min Act: -0.1700
Data Index: 3885530 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5412. Min Range: -6.5412
Max Act: 6.3849. Min Act: -0.1700
Data Index: 2555884 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5412. Min Range: -6.5412
Max Act: 6.3849. Min Act: -0.1700
Data Index: 3572152 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5412. Min Range: -6.5412
Max Act: 6.2599. Min Act: -0.1700
Data Index: 6529175 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5412. Min Range: -6.5412
Max Act: 6.2912. Min Act: -0.1700
Data Index: 6914132 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5412. Min Range: -6.5412
Max Act: 6.2599. Min Act: -0.1700
Data Index: 7405662 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5412. Min Range: -6.5412
Max Act: 6.1974. Min Act: -0.1700
Data Index: 7331127 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5412. Min Range: -6.5412
Max Act: 6.2287. Min Act: -0.1700
Data Index: 7494853 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5412. Min Range: -6.5412
Max Act: 6.1349. Min Act: -0.1700
Data Index: 2674837 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5412. Min Range: -6.5412
Max Act: 6.1662. Min Act: -0.1700
Data Index: 7602946 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5412. Min Range: -6.5412
Max Act: 6.1349. Min Act: -0.1700
Data Index: 5932472 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5412. Min Range: -6.5412
Max Act: 6.1349. Min Act: -0.1700
Data Index: 4817500 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5412. Min Range: -6.5412
Max Act: 6.1349. Min Act: -0.1700
Data Index: 2800802 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5412. Min Range: -6.5412
Max Act: 6.1349. Min Act: -0.1700
Data Index: 5313614 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5412. Min Range: -6.5412
Max Act: 6.1037. Min Act: -0.1700
Data Index: 1437683 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5412. Min Range: -6.5412
Max Act: 6.1037. Min Act: -0.1700
Data Index: 1476323 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5412. Min Range: -6.5412
Max Act: 6.1037. Min Act: -0.1700
Data Index: 9578 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5412. Min Range: -6.5412
Max Act: 6.1037. Min Act: -0.1700
Data Index: 2734737 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5412. Min Range: -6.5412
Max Act: 6.1037. Min Act: -0.1700
Data Index: 5362549 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19