Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 30 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8632. Min Range: -2.8632
Max Act: 2.8632. Min Act: -0.1700
Data Index: 7808185 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8632. Min Range: -2.8632
Max Act: 2.7837. Min Act: -0.1700
Data Index: 8430220 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8632. Min Range: -2.8632
Max Act: 2.6879. Min Act: -0.1700
Data Index: 165778 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8632. Min Range: -2.8632
Max Act: 2.6718. Min Act: -0.1700
Data Index: 7867298 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8632. Min Range: -2.8632
Max Act: 2.6879. Min Act: -0.1700
Data Index: 7873231 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8632. Min Range: -2.8632
Max Act: 2.6879. Min Act: -0.1700
Data Index: 4168704 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8632. Min Range: -2.8632
Max Act: 2.6718. Min Act: -0.1700
Data Index: 2963336 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8632. Min Range: -2.8632
Max Act: 2.6558. Min Act: -0.1700
Data Index: 5310770 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8632. Min Range: -2.8632
Max Act: 2.6558. Min Act: -0.1700
Data Index: 4807955 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8632. Min Range: -2.8632
Max Act: 2.6718. Min Act: -0.1700
Data Index: 3850376 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8632. Min Range: -2.8632
Max Act: 2.6398. Min Act: -0.1700
Data Index: 8353533 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8632. Min Range: -2.8632
Max Act: 2.6558. Min Act: -0.1700
Data Index: 3273415 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8632. Min Range: -2.8632
Max Act: 2.6398. Min Act: -0.1700
Data Index: 3198733 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8632. Min Range: -2.8632
Max Act: 2.6237. Min Act: -0.1700
Data Index: 8461203 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8632. Min Range: -2.8632
Max Act: 2.6398. Min Act: -0.1700
Data Index: 3365880 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8632. Min Range: -2.8632
Max Act: 2.6237. Min Act: -0.1700
Data Index: 8225117 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8632. Min Range: -2.8632
Max Act: 2.6237. Min Act: -0.1700
Data Index: 4211159 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8632. Min Range: -2.8632
Max Act: 2.6398. Min Act: -0.1700
Data Index: 8454770 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8632. Min Range: -2.8632
Max Act: 2.5915. Min Act: -0.1700
Data Index: 5166817 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8632. Min Range: -2.8632
Max Act: 2.5915. Min Act: -0.1700
Data Index: 4881466 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19