Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3329 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9394. Min Range: -6.9394
Max Act: 6.9394. Min Act: -0.1700
Data Index: 7414925 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9394. Min Range: -6.9394
Max Act: 6.6894. Min Act: -0.1700
Data Index: 2787006 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9394. Min Range: -6.9394
Max Act: 6.5331. Min Act: -0.1700
Data Index: 6659188 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9394. Min Range: -6.9394
Max Act: 6.4706. Min Act: -0.1700
Data Index: 1791339 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9394. Min Range: -6.9394
Max Act: 6.4706. Min Act: -0.1700
Data Index: 1313722 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9394. Min Range: -6.9394
Max Act: 6.4394. Min Act: -0.1700
Data Index: 7997379 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9394. Min Range: -6.9394
Max Act: 6.4706. Min Act: -0.1700
Data Index: 6649482 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9394. Min Range: -6.9394
Max Act: 6.4081. Min Act: -0.1700
Data Index: 926133 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9394. Min Range: -6.9394
Max Act: 6.4394. Min Act: -0.1700
Data Index: 8192736 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9394. Min Range: -6.9394
Max Act: 6.4081. Min Act: -0.1700
Data Index: 3989704 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9394. Min Range: -6.9394
Max Act: 6.3456. Min Act: -0.1700
Data Index: 564392 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9394. Min Range: -6.9394
Max Act: 6.4081. Min Act: -0.1700
Data Index: 5058822 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9394. Min Range: -6.9394
Max Act: 6.4081. Min Act: -0.1700
Data Index: 5206111 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9394. Min Range: -6.9394
Max Act: 6.3456. Min Act: -0.1700
Data Index: 7497922 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9394. Min Range: -6.9394
Max Act: 6.3456. Min Act: -0.1700
Data Index: 3175041 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9394. Min Range: -6.9394
Max Act: 6.3456. Min Act: -0.1700
Data Index: 4294133 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9394. Min Range: -6.9394
Max Act: 6.2831. Min Act: -0.1700
Data Index: 4496311 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9394. Min Range: -6.9394
Max Act: 6.3144. Min Act: -0.1700
Data Index: 6566409 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9394. Min Range: -6.9394
Max Act: 6.2831. Min Act: -0.1700
Data Index: 3553032 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9394. Min Range: -6.9394
Max Act: 6.2831. Min Act: -0.1700
Data Index: 5823983 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19