Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4095 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8166. Min Range: -4.8166
Max Act: 4.8166. Min Act: -0.1700
Data Index: 7185306 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8166. Min Range: -4.8166
Max Act: 4.8166. Min Act: -0.1700
Data Index: 2859808 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8166. Min Range: -4.8166
Max Act: 4.7853. Min Act: -0.1700
Data Index: 2129464 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8166. Min Range: -4.8166
Max Act: 4.6916. Min Act: -0.1700
Data Index: 1707870 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8166. Min Range: -4.8166
Max Act: 4.6291. Min Act: -0.1700
Data Index: 1731457 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8166. Min Range: -4.8166
Max Act: 4.5666. Min Act: -0.1700
Data Index: 3625388 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8166. Min Range: -4.8166
Max Act: 4.5666. Min Act: -0.1700
Data Index: 1806619 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8166. Min Range: -4.8166
Max Act: 4.5353. Min Act: -0.1700
Data Index: 8545522 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8166. Min Range: -4.8166
Max Act: 4.5041. Min Act: -0.1700
Data Index: 4971442 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8166. Min Range: -4.8166
Max Act: 4.5666. Min Act: -0.1700
Data Index: 979940 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8166. Min Range: -4.8166
Max Act: 4.5353. Min Act: -0.1700
Data Index: 2306518 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8166. Min Range: -4.8166
Max Act: 4.5041. Min Act: -0.1700
Data Index: 3767307 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8166. Min Range: -4.8166
Max Act: 4.4728. Min Act: -0.1700
Data Index: 3470183 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8166. Min Range: -4.8166
Max Act: 4.5041. Min Act: -0.1700
Data Index: 452729 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8166. Min Range: -4.8166
Max Act: 4.5666. Min Act: -0.1700
Data Index: 8639556 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8166. Min Range: -4.8166
Max Act: 4.4728. Min Act: -0.1700
Data Index: 3903901 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8166. Min Range: -4.8166
Max Act: 4.5041. Min Act: -0.1700
Data Index: 2462491 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8166. Min Range: -4.8166
Max Act: 4.5353. Min Act: -0.1700
Data Index: 6997160 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8166. Min Range: -4.8166
Max Act: 4.5041. Min Act: -0.1700
Data Index: 4980935 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8166. Min Range: -4.8166
Max Act: 4.5041. Min Act: -0.1700
Data Index: 6678800 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19