Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 777 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6034. Min Range: -3.6034
Max Act: 3.6034. Min Act: -0.1700
Data Index: 7195606 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6034. Min Range: -3.6034
Max Act: 3.5251. Min Act: -0.1700
Data Index: 3705773 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6034. Min Range: -3.6034
Max Act: 3.5408. Min Act: -0.1700
Data Index: 3413442 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6034. Min Range: -3.6034
Max Act: 3.5094. Min Act: -0.1700
Data Index: 3786662 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6034. Min Range: -3.6034
Max Act: 3.4468. Min Act: -0.1700
Data Index: 2575447 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6034. Min Range: -3.6034
Max Act: 3.3998. Min Act: -0.1700
Data Index: 438279 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6034. Min Range: -3.6034
Max Act: 3.4311. Min Act: -0.1700
Data Index: 8114935 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6034. Min Range: -3.6034
Max Act: 3.3684. Min Act: -0.1700
Data Index: 5291365 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6034. Min Range: -3.6034
Max Act: 3.3370. Min Act: -0.1700
Data Index: 500165 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6034. Min Range: -3.6034
Max Act: 3.3213. Min Act: -0.1700
Data Index: 2740546 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6034. Min Range: -3.6034
Max Act: 3.3370. Min Act: -0.1700
Data Index: 8812984 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6034. Min Range: -3.6034
Max Act: 3.3370. Min Act: -0.1700
Data Index: 27547 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6034. Min Range: -3.6034
Max Act: 3.3213. Min Act: -0.1700
Data Index: 338525 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6034. Min Range: -3.6034
Max Act: 3.3056. Min Act: -0.1700
Data Index: 8068555 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6034. Min Range: -3.6034
Max Act: 3.3056. Min Act: -0.1700
Data Index: 8431559 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6034. Min Range: -3.6034
Max Act: 3.2899. Min Act: -0.1700
Data Index: 839646 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6034. Min Range: -3.6034
Max Act: 3.3056. Min Act: -0.1700
Data Index: 3540069 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6034. Min Range: -3.6034
Max Act: 3.3056. Min Act: -0.1700
Data Index: 512993 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6034. Min Range: -3.6034
Max Act: 3.3056. Min Act: -0.1700
Data Index: 3845582 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6034. Min Range: -3.6034
Max Act: 3.2899. Min Act: -0.1700
Data Index: 1291995 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19