Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3332 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8553. Min Range: -5.8553
Max Act: 5.8553. Min Act: -0.1700
Data Index: 4592831 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8553. Min Range: -5.8553
Max Act: 5.8553. Min Act: -0.1700
Data Index: 4903304 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8553. Min Range: -5.8553
Max Act: 5.8241. Min Act: -0.1700
Data Index: 3023797 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8553. Min Range: -5.8553
Max Act: 5.8553. Min Act: -0.1700
Data Index: 3754157 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8553. Min Range: -5.8553
Max Act: 5.7303. Min Act: -0.1700
Data Index: 680000 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8553. Min Range: -5.8553
Max Act: 5.7616. Min Act: -0.1700
Data Index: 464749 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8553. Min Range: -5.8553
Max Act: 5.7303. Min Act: -0.1700
Data Index: 7289750 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8553. Min Range: -5.8553
Max Act: 5.7303. Min Act: -0.1700
Data Index: 7714704 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8553. Min Range: -5.8553
Max Act: 5.6991. Min Act: -0.1700
Data Index: 1650504 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8553. Min Range: -5.8553
Max Act: 5.6678. Min Act: -0.1700
Data Index: 3454492 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8553. Min Range: -5.8553
Max Act: 5.6678. Min Act: -0.1700
Data Index: 8016815 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8553. Min Range: -5.8553
Max Act: 5.6678. Min Act: -0.1700
Data Index: 1415884 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8553. Min Range: -5.8553
Max Act: 5.6678. Min Act: -0.1700
Data Index: 6140077 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8553. Min Range: -5.8553
Max Act: 5.6678. Min Act: -0.1700
Data Index: 8715410 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8553. Min Range: -5.8553
Max Act: 5.6366. Min Act: -0.1700
Data Index: 8703662 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8553. Min Range: -5.8553
Max Act: 5.6366. Min Act: -0.1700
Data Index: 5630919 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8553. Min Range: -5.8553
Max Act: 5.6678. Min Act: -0.1700
Data Index: 2718060 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8553. Min Range: -5.8553
Max Act: 5.6366. Min Act: -0.1700
Data Index: 1930547 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8553. Min Range: -5.8553
Max Act: 5.6053. Min Act: -0.1700
Data Index: 2935544 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8553. Min Range: -5.8553
Max Act: 5.6053. Min Act: -0.1700
Data Index: 628111 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19