Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3128 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5245. Min Range: -1.5245
Max Act: 1.5245. Min Act: -0.1700
Data Index: 1327245 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5245. Min Range: -1.5245
Max Act: 1.5069. Min Act: -0.1697
Data Index: 681079 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5245. Min Range: -1.5245
Max Act: 1.4454. Min Act: -0.1697
Data Index: 2468721 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5245. Min Range: -1.5245
Max Act: 1.4278. Min Act: -0.1677
Data Index: 7151704 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5245. Min Range: -1.5245
Max Act: 1.4278. Min Act: -0.1700
Data Index: 227083 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5245. Min Range: -1.5245
Max Act: 1.4190. Min Act: -0.1700
Data Index: 4348437 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5245. Min Range: -1.5245
Max Act: 1.4278. Min Act: -0.1700
Data Index: 2781710 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5245. Min Range: -1.5245
Max Act: 1.4190. Min Act: -0.1700
Data Index: 4014063 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5245. Min Range: -1.5245
Max Act: 1.4102. Min Act: -0.1699
Data Index: 4425540 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5245. Min Range: -1.5245
Max Act: 1.4014. Min Act: -0.1700
Data Index: 2246997 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5245. Min Range: -1.5245
Max Act: 1.4190. Min Act: -0.1700
Data Index: 1484888 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5245. Min Range: -1.5245
Max Act: 1.4014. Min Act: -0.1700
Data Index: 4298922 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5245. Min Range: -1.5245
Max Act: 1.4014. Min Act: -0.1692
Data Index: 2080443 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5245. Min Range: -1.5245
Max Act: 1.4014. Min Act: -0.1700
Data Index: 1176911 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5245. Min Range: -1.5245
Max Act: 1.3926. Min Act: -0.1700
Data Index: 5995653 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5245. Min Range: -1.5245
Max Act: 1.3926. Min Act: -0.1700
Data Index: 4884415 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5245. Min Range: -1.5245
Max Act: 1.3926. Min Act: -0.1700
Data Index: 1546884 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5245. Min Range: -1.5245
Max Act: 1.3750. Min Act: -0.1700
Data Index: 3561758 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5245. Min Range: -1.5245
Max Act: 1.3838. Min Act: -0.1700
Data Index: 120332 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5245. Min Range: -1.5245
Max Act: 1.3838. Min Act: -0.1695
Data Index: 1655333 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19