Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 732 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9588. Min Range: -3.9588
Max Act: 3.9588. Min Act: -0.1700
Data Index: 7261807 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9588. Min Range: -3.9588
Max Act: 3.7399. Min Act: -0.1700
Data Index: 6675030 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9588. Min Range: -3.9588
Max Act: 3.7869. Min Act: -0.1700
Data Index: 3830902 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9588. Min Range: -3.9588
Max Act: 3.6774. Min Act: -0.1700
Data Index: 7782454 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9588. Min Range: -3.9588
Max Act: 3.6774. Min Act: -0.1700
Data Index: 1344349 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9588. Min Range: -3.9588
Max Act: 3.5835. Min Act: -0.1700
Data Index: 339042 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9588. Min Range: -3.9588
Max Act: 3.5991. Min Act: -0.1700
Data Index: 8740771 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9588. Min Range: -3.9588
Max Act: 3.5678. Min Act: -0.1700
Data Index: 1977119 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9588. Min Range: -3.9588
Max Act: 3.5208. Min Act: -0.1700
Data Index: 4363435 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9588. Min Range: -3.9588
Max Act: 3.4582. Min Act: -0.1700
Data Index: 2866124 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9588. Min Range: -3.9588
Max Act: 3.4895. Min Act: -0.1700
Data Index: 5435693 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9588. Min Range: -3.9588
Max Act: 3.4739. Min Act: -0.1700
Data Index: 773371 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9588. Min Range: -3.9588
Max Act: 3.4739. Min Act: -0.1700
Data Index: 5289596 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9588. Min Range: -3.9588
Max Act: 3.4112. Min Act: -0.1700
Data Index: 5181145 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9588. Min Range: -3.9588
Max Act: 3.4425. Min Act: -0.1700
Data Index: 8221487 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9588. Min Range: -3.9588
Max Act: 3.4425. Min Act: -0.1700
Data Index: 7555429 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9588. Min Range: -3.9588
Max Act: 3.4112. Min Act: -0.1700
Data Index: 3896996 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9588. Min Range: -3.9588
Max Act: 3.3798. Min Act: -0.1700
Data Index: 8001809 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9588. Min Range: -3.9588
Max Act: 3.3798. Min Act: -0.1700
Data Index: 3674539 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9588. Min Range: -3.9588
Max Act: 3.3798. Min Act: -0.1700
Data Index: 7270413 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19