Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 64 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.9688. Min Range: -7.9688
Max Act: 7.9688. Min Act: -0.1700
Data Index: 6883746 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9688. Min Range: -7.9688
Max Act: 7.7501. Min Act: -0.1700
Data Index: 767596 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9688. Min Range: -7.9688
Max Act: 7.5938. Min Act: -0.1700
Data Index: 5421308 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9688. Min Range: -7.9688
Max Act: 7.4688. Min Act: -0.1700
Data Index: 5141034 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9688. Min Range: -7.9688
Max Act: 7.4063. Min Act: -0.1700
Data Index: 5710942 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9688. Min Range: -7.9688
Max Act: 7.2813. Min Act: -0.1700
Data Index: 7612712 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9688. Min Range: -7.9688
Max Act: 7.1563. Min Act: -0.1700
Data Index: 1024592 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9688. Min Range: -7.9688
Max Act: 7.2188. Min Act: -0.1700
Data Index: 2165143 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9688. Min Range: -7.9688
Max Act: 7.1876. Min Act: -0.1700
Data Index: 3534961 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9688. Min Range: -7.9688
Max Act: 7.1563. Min Act: -0.1700
Data Index: 836428 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9688. Min Range: -7.9688
Max Act: 7.0313. Min Act: -0.1700
Data Index: 2911185 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9688. Min Range: -7.9688
Max Act: 7.0001. Min Act: -0.1700
Data Index: 5137071 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9688. Min Range: -7.9688
Max Act: 6.9376. Min Act: -0.1700
Data Index: 2749850 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9688. Min Range: -7.9688
Max Act: 6.9376. Min Act: -0.1700
Data Index: 6884330 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9688. Min Range: -7.9688
Max Act: 6.9063. Min Act: -0.1700
Data Index: 4112477 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9688. Min Range: -7.9688
Max Act: 6.8126. Min Act: -0.1700
Data Index: 170919 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9688. Min Range: -7.9688
Max Act: 6.9063. Min Act: -0.1700
Data Index: 6656745 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9688. Min Range: -7.9688
Max Act: 6.9376. Min Act: -0.1700
Data Index: 4974938 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9688. Min Range: -7.9688
Max Act: 6.9376. Min Act: -0.1700
Data Index: 3842763 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9688. Min Range: -7.9688
Max Act: 6.9063. Min Act: -0.1700
Data Index: 3428503 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19