Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2417 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6745. Min Range: -5.6745
Max Act: 5.6745. Min Act: -0.1700
Data Index: 8769863 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6745. Min Range: -5.6745
Max Act: 5.6745. Min Act: -0.1700
Data Index: 7805246 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6745. Min Range: -5.6745
Max Act: 5.6745. Min Act: -0.1700
Data Index: 5831686 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6745. Min Range: -5.6745
Max Act: 5.6120. Min Act: -0.1700
Data Index: 8218784 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6745. Min Range: -5.6745
Max Act: 5.6120. Min Act: -0.1700
Data Index: 927491 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6745. Min Range: -5.6745
Max Act: 5.5807. Min Act: -0.1700
Data Index: 8020404 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6745. Min Range: -5.6745
Max Act: 5.6120. Min Act: -0.1700
Data Index: 2004544 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6745. Min Range: -5.6745
Max Act: 5.5807. Min Act: -0.1700
Data Index: 87496 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6745. Min Range: -5.6745
Max Act: 5.5807. Min Act: -0.1700
Data Index: 1920276 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6745. Min Range: -5.6745
Max Act: 5.5807. Min Act: -0.1700
Data Index: 4493658 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6745. Min Range: -5.6745
Max Act: 5.5807. Min Act: -0.1700
Data Index: 2331681 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6745. Min Range: -5.6745
Max Act: 5.5495. Min Act: -0.1700
Data Index: 2625733 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6745. Min Range: -5.6745
Max Act: 5.5182. Min Act: -0.1700
Data Index: 2824441 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6745. Min Range: -5.6745
Max Act: 5.5495. Min Act: -0.1700
Data Index: 5054873 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6745. Min Range: -5.6745
Max Act: 5.5182. Min Act: -0.1700
Data Index: 4840975 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6745. Min Range: -5.6745
Max Act: 5.4870. Min Act: -0.1700
Data Index: 821764 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6745. Min Range: -5.6745
Max Act: 5.5182. Min Act: -0.1700
Data Index: 2069425 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6745. Min Range: -5.6745
Max Act: 5.5182. Min Act: -0.1700
Data Index: 4567493 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6745. Min Range: -5.6745
Max Act: 5.5182. Min Act: -0.1700
Data Index: 29507 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6745. Min Range: -5.6745
Max Act: 5.5182. Min Act: -0.1700
Data Index: 1800042 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19