Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2134 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.6401. Min Act: -0.1700
Data Index: 4208326 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.5776. Min Act: -0.1700
Data Index: 6646570 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.6088. Min Act: -0.1700
Data Index: 322266 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.5776. Min Act: -0.1700
Data Index: 6941602 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.5463. Min Act: -0.1700
Data Index: 6420185 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.5463. Min Act: -0.1700
Data Index: 1429442 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.5463. Min Act: -0.1700
Data Index: 4604561 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.5151. Min Act: -0.1700
Data Index: 5728349 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.5151. Min Act: -0.1700
Data Index: 1808493 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.5151. Min Act: -0.1700
Data Index: 7430401 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.5151. Min Act: -0.1700
Data Index: 498878 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.4838. Min Act: -0.1700
Data Index: 1673450 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.4838. Min Act: -0.1699
Data Index: 4558292 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.4838. Min Act: -0.1700
Data Index: 7223723 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.4838. Min Act: -0.1700
Data Index: 1429444 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.4838. Min Act: -0.1700
Data Index: 3204807 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.4838. Min Act: -0.1700
Data Index: 7469861 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.4526. Min Act: -0.1700
Data Index: 1429443 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.4526. Min Act: -0.1700
Data Index: 4669344 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6401. Min Range: -4.6401
Max Act: 4.4526. Min Act: -0.1700
Data Index: 1665906 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19