Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3448 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2501. Min Range: -5.2501
Max Act: 5.2501. Min Act: -0.1700
Data Index: 3636818 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2501. Min Range: -5.2501
Max Act: 5.1563. Min Act: -0.1700
Data Index: 7129718 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2501. Min Range: -5.2501
Max Act: 5.0938. Min Act: -0.1700
Data Index: 2976610 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2501. Min Range: -5.2501
Max Act: 5.0626. Min Act: -0.1700
Data Index: 5633453 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2501. Min Range: -5.2501
Max Act: 5.0626. Min Act: -0.1700
Data Index: 7893930 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2501. Min Range: -5.2501
Max Act: 5.0313. Min Act: -0.1700
Data Index: 6846025 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2501. Min Range: -5.2501
Max Act: 5.0313. Min Act: -0.1700
Data Index: 3318938 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2501. Min Range: -5.2501
Max Act: 5.0626. Min Act: -0.1700
Data Index: 4312335 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2501. Min Range: -5.2501
Max Act: 4.9688. Min Act: -0.1700
Data Index: 5646574 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2501. Min Range: -5.2501
Max Act: 5.0001. Min Act: -0.1700
Data Index: 7108154 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2501. Min Range: -5.2501
Max Act: 5.0313. Min Act: -0.1700
Data Index: 659006 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2501. Min Range: -5.2501
Max Act: 4.9688. Min Act: -0.1700
Data Index: 2895028 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2501. Min Range: -5.2501
Max Act: 4.9376. Min Act: -0.1700
Data Index: 1399890 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2501. Min Range: -5.2501
Max Act: 4.9376. Min Act: -0.1700
Data Index: 5750298 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2501. Min Range: -5.2501
Max Act: 4.9063. Min Act: -0.1700
Data Index: 1679280 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2501. Min Range: -5.2501
Max Act: 4.9376. Min Act: -0.1700
Data Index: 1795085 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2501. Min Range: -5.2501
Max Act: 4.9376. Min Act: -0.1700
Data Index: 1190784 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2501. Min Range: -5.2501
Max Act: 4.9688. Min Act: -0.1700
Data Index: 635538 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2501. Min Range: -5.2501
Max Act: 4.9376. Min Act: -0.1700
Data Index: 6824661 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2501. Min Range: -5.2501
Max Act: 4.9376. Min Act: -0.1700
Data Index: 7149437 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19