Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1739 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.8467. Min Act: -0.1700
Data Index: 1970738 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.7217. Min Act: -0.1700
Data Index: 7439085 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5342. Min Act: -0.1700
Data Index: 2459753 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.4092. Min Act: -0.1700
Data Index: 1117694 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.2842. Min Act: -0.1700
Data Index: 221348 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.2529. Min Act: -0.1700
Data Index: 7795543 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.2842. Min Act: -0.1700
Data Index: 3324824 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.1904. Min Act: -0.1700
Data Index: 8560546 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.1904. Min Act: -0.1700
Data Index: 4029496 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.1904. Min Act: -0.1700
Data Index: 6918150 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.1592. Min Act: -0.1700
Data Index: 5205047 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.1592. Min Act: -0.1700
Data Index: 3592915 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.1904. Min Act: -0.1700
Data Index: 5833512 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.1279. Min Act: -0.1700
Data Index: 2491730 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.1592. Min Act: -0.1700
Data Index: 4266899 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.1904. Min Act: -0.1700
Data Index: 6183192 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.1592. Min Act: -0.1700
Data Index: 1945733 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.0654. Min Act: -0.1700
Data Index: 5408469 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.0966. Min Act: -0.1700
Data Index: 5814157 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.1592. Min Act: -0.1700
Data Index: 3436211 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19