Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2749 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.7115. Min Act: -0.1700
Data Index: 5829118 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.7115. Min Act: -0.1700
Data Index: 1844242 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.6803. Min Act: -0.1700
Data Index: 1850807 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.6490. Min Act: -0.1700
Data Index: 3944927 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.6490. Min Act: -0.1700
Data Index: 6782163 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.6490. Min Act: -0.1700
Data Index: 6518885 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.6178. Min Act: -0.1700
Data Index: 2306273 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.6178. Min Act: -0.1700
Data Index: 2013331 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.6178. Min Act: -0.1700
Data Index: 56326 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.5865. Min Act: -0.1700
Data Index: 4630641 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.5865. Min Act: -0.1700
Data Index: 6111020 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.5240. Min Act: -0.1700
Data Index: 6901778 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.5240. Min Act: -0.1700
Data Index: 7443805 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.4928. Min Act: -0.1700
Data Index: 8672565 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.4928. Min Act: -0.1700
Data Index: 2414723 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.4615. Min Act: -0.1700
Data Index: 6453101 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.4928. Min Act: -0.1700
Data Index: 3890626 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.4928. Min Act: -0.1700
Data Index: 1583137 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.4615. Min Act: -0.1700
Data Index: 5541129 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7115. Min Range: -4.7115
Max Act: 4.4615. Min Act: -0.1700
Data Index: 2587473 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19