Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3059 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9966. Min Range: -4.9966
Max Act: 4.9966. Min Act: -0.1700
Data Index: 7532764 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9966. Min Range: -4.9966
Max Act: 4.9341. Min Act: -0.1700
Data Index: 7900263 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9966. Min Range: -4.9966
Max Act: 4.9341. Min Act: -0.1700
Data Index: 1828958 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9966. Min Range: -4.9966
Max Act: 4.8716. Min Act: -0.1700
Data Index: 7916344 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9966. Min Range: -4.9966
Max Act: 4.8091. Min Act: -0.1700
Data Index: 7030747 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9966. Min Range: -4.9966
Max Act: 4.8403. Min Act: -0.1700
Data Index: 8497001 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9966. Min Range: -4.9966
Max Act: 4.8091. Min Act: -0.1700
Data Index: 8421967 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9966. Min Range: -4.9966
Max Act: 4.7466. Min Act: -0.1700
Data Index: 3275670 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9966. Min Range: -4.9966
Max Act: 4.7466. Min Act: -0.1700
Data Index: 8701556 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9966. Min Range: -4.9966
Max Act: 4.7466. Min Act: -0.1700
Data Index: 4549944 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9966. Min Range: -4.9966
Max Act: 4.6841. Min Act: -0.1700
Data Index: 8720047 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9966. Min Range: -4.9966
Max Act: 4.7466. Min Act: -0.1700
Data Index: 4761819 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9966. Min Range: -4.9966
Max Act: 4.7153. Min Act: -0.1700
Data Index: 6064465 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9966. Min Range: -4.9966
Max Act: 4.7153. Min Act: -0.1700
Data Index: 5290395 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9966. Min Range: -4.9966
Max Act: 4.7466. Min Act: -0.1700
Data Index: 2062153 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9966. Min Range: -4.9966
Max Act: 4.6528. Min Act: -0.1700
Data Index: 7160 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9966. Min Range: -4.9966
Max Act: 4.6841. Min Act: -0.1700
Data Index: 6540142 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9966. Min Range: -4.9966
Max Act: 4.6528. Min Act: -0.1700
Data Index: 3438999 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9966. Min Range: -4.9966
Max Act: 4.6216. Min Act: -0.1700
Data Index: 5829908 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9966. Min Range: -4.9966
Max Act: 4.6216. Min Act: -0.1700
Data Index: 4934332 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19