Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2960 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9285. Min Range: -1.9285
Max Act: 1.9285. Min Act: -0.1700
Data Index: 1766943 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9285. Min Range: -1.9285
Max Act: 1.9285. Min Act: -0.1700
Data Index: 1796640 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9285. Min Range: -1.9285
Max Act: 1.9115. Min Act: -0.1700
Data Index: 2222272 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9285. Min Range: -1.9285
Max Act: 1.8774. Min Act: -0.1700
Data Index: 7419114 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9285. Min Range: -1.9285
Max Act: 1.8603. Min Act: -0.1696
Data Index: 5828745 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9285. Min Range: -1.9285
Max Act: 1.8603. Min Act: -0.1700
Data Index: 8168567 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9285. Min Range: -1.9285
Max Act: 1.8431. Min Act: -0.1700
Data Index: 3279589 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9285. Min Range: -1.9285
Max Act: 1.8774. Min Act: -0.1700
Data Index: 1820905 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9285. Min Range: -1.9285
Max Act: 1.8603. Min Act: -0.1699
Data Index: 1452708 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9285. Min Range: -1.9285
Max Act: 1.8774. Min Act: -0.1700
Data Index: 4898505 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9285. Min Range: -1.9285
Max Act: 1.8431. Min Act: -0.1700
Data Index: 5777077 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9285. Min Range: -1.9285
Max Act: 1.8603. Min Act: -0.1700
Data Index: 5032133 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9285. Min Range: -1.9285
Max Act: 1.8431. Min Act: -0.1700
Data Index: 2701991 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9285. Min Range: -1.9285
Max Act: 1.8260. Min Act: -0.1700
Data Index: 193269 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9285. Min Range: -1.9285
Max Act: 1.8431. Min Act: -0.1700
Data Index: 8783194 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9285. Min Range: -1.9285
Max Act: 1.8260. Min Act: -0.1700
Data Index: 7398040 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9285. Min Range: -1.9285
Max Act: 1.8260. Min Act: -0.1700
Data Index: 5093539 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9285. Min Range: -1.9285
Max Act: 1.8260. Min Act: -0.1700
Data Index: 2859163 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9285. Min Range: -1.9285
Max Act: 1.8088. Min Act: -0.1700
Data Index: 333605 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9285. Min Range: -1.9285
Max Act: 1.8260. Min Act: -0.1700
Data Index: 5474240 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19