Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1850 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.7872. Min Act: -0.1700
Data Index: 1144877 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.5997. Min Act: -0.1700
Data Index: 7564315 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.5997. Min Act: -0.1700
Data Index: 4059284 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.6310. Min Act: -0.1700
Data Index: 202366 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.6310. Min Act: -0.1700
Data Index: 4767774 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.5997. Min Act: -0.1700
Data Index: 6077129 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.5685. Min Act: -0.1700
Data Index: 3143837 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.5685. Min Act: -0.1700
Data Index: 215828 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.5372. Min Act: -0.1700
Data Index: 8307087 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.4747. Min Act: -0.1700
Data Index: 8659701 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.5060. Min Act: -0.1700
Data Index: 3639806 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.4747. Min Act: -0.1700
Data Index: 4167812 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.5060. Min Act: -0.1700
Data Index: 2161988 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.4747. Min Act: -0.1700
Data Index: 263268 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.4747. Min Act: -0.1700
Data Index: 3817770 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.4122. Min Act: -0.1700
Data Index: 7541821 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.3810. Min Act: -0.1700
Data Index: 4103033 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.3810. Min Act: -0.1700
Data Index: 742515 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.3810. Min Act: -0.1700
Data Index: 6637986 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7872. Min Range: -6.7872
Max Act: 6.3810. Min Act: -0.1700
Data Index: 6839102 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19