Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3026 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6906. Min Range: -4.6906
Max Act: 4.6906. Min Act: -0.1700
Data Index: 6220926 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6906. Min Range: -4.6906
Max Act: 4.6594. Min Act: -0.1700
Data Index: 1847426 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6906. Min Range: -4.6906
Max Act: 4.6906. Min Act: -0.1700
Data Index: 6022657 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6906. Min Range: -4.6906
Max Act: 4.6594. Min Act: -0.1700
Data Index: 4601027 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6906. Min Range: -4.6906
Max Act: 4.5969. Min Act: -0.1700
Data Index: 786127 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6906. Min Range: -4.6906
Max Act: 4.5969. Min Act: -0.1700
Data Index: 359381 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6906. Min Range: -4.6906
Max Act: 4.5969. Min Act: -0.1700
Data Index: 5324676 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6906. Min Range: -4.6906
Max Act: 4.5969. Min Act: -0.1700
Data Index: 6035343 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6906. Min Range: -4.6906
Max Act: 4.5656. Min Act: -0.1700
Data Index: 7815648 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6906. Min Range: -4.6906
Max Act: 4.5344. Min Act: -0.1700
Data Index: 3869476 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6906. Min Range: -4.6906
Max Act: 4.5344. Min Act: -0.1700
Data Index: 2092908 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6906. Min Range: -4.6906
Max Act: 4.5344. Min Act: -0.1700
Data Index: 3535317 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6906. Min Range: -4.6906
Max Act: 4.5344. Min Act: -0.1700
Data Index: 5061134 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6906. Min Range: -4.6906
Max Act: 4.5656. Min Act: -0.1700
Data Index: 7260461 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6906. Min Range: -4.6906
Max Act: 4.5031. Min Act: -0.1700
Data Index: 7620910 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6906. Min Range: -4.6906
Max Act: 4.5031. Min Act: -0.1700
Data Index: 3824368 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6906. Min Range: -4.6906
Max Act: 4.5344. Min Act: -0.1700
Data Index: 7023492 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6906. Min Range: -4.6906
Max Act: 4.4719. Min Act: -0.1700
Data Index: 6408900 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6906. Min Range: -4.6906
Max Act: 4.4719. Min Act: -0.1700
Data Index: 1980681 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6906. Min Range: -4.6906
Max Act: 4.4719. Min Act: -0.1700
Data Index: 783668 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19