Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 75 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.9704. Min Act: -0.1698
Data Index: 5988757 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.9392. Min Act: -0.1700
Data Index: 6373330 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.9079. Min Act: -0.1700
Data Index: 908709 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.9079. Min Act: -0.1700
Data Index: 4840763 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8766. Min Act: -0.1700
Data Index: 4365501 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8766. Min Act: -0.1700
Data Index: 3682373 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8766. Min Act: -0.1700
Data Index: 7134745 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8766. Min Act: -0.1699
Data Index: 5400857 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8766. Min Act: -0.1700
Data Index: 4443949 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8766. Min Act: -0.1700
Data Index: 4076845 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8454. Min Act: -0.1700
Data Index: 2237554 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8454. Min Act: -0.1700
Data Index: 5162470 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8454. Min Act: -0.1700
Data Index: 1854965 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8141. Min Act: -0.1700
Data Index: 6479413 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8454. Min Act: -0.1700
Data Index: 7447122 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8454. Min Act: -0.1700
Data Index: 7992477 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8454. Min Act: -0.1700
Data Index: 3202827 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8454. Min Act: -0.1700
Data Index: 3511451 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8454. Min Act: -0.1700
Data Index: 521174 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8141. Min Act: -0.1700
Data Index: 3943959 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19