Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3842 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8128. Min Range: -4.8128
Max Act: 4.8128. Min Act: -0.1700
Data Index: 7328338 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8128. Min Range: -4.8128
Max Act: 4.7503. Min Act: -0.1700
Data Index: 58413 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8128. Min Range: -4.8128
Max Act: 4.7816. Min Act: -0.1700
Data Index: 2316831 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8128. Min Range: -4.8128
Max Act: 4.6878. Min Act: -0.1700
Data Index: 840000 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8128. Min Range: -4.8128
Max Act: 4.6566. Min Act: -0.1700
Data Index: 6022254 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8128. Min Range: -4.8128
Max Act: 4.6253. Min Act: -0.1700
Data Index: 4515285 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8128. Min Range: -4.8128
Max Act: 4.6253. Min Act: -0.1700
Data Index: 1569494 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8128. Min Range: -4.8128
Max Act: 4.6253. Min Act: -0.1700
Data Index: 2761428 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8128. Min Range: -4.8128
Max Act: 4.6253. Min Act: -0.1700
Data Index: 953430 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8128. Min Range: -4.8128
Max Act: 4.6253. Min Act: -0.1700
Data Index: 4245490 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8128. Min Range: -4.8128
Max Act: 4.5628. Min Act: -0.1700
Data Index: 450329 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8128. Min Range: -4.8128
Max Act: 4.5941. Min Act: -0.1700
Data Index: 782366 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8128. Min Range: -4.8128
Max Act: 4.5941. Min Act: -0.1700
Data Index: 947572 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8128. Min Range: -4.8128
Max Act: 4.5941. Min Act: -0.1700
Data Index: 8823859 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8128. Min Range: -4.8128
Max Act: 4.5941. Min Act: -0.1700
Data Index: 8369809 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8128. Min Range: -4.8128
Max Act: 4.5941. Min Act: -0.1700
Data Index: 6390223 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8128. Min Range: -4.8128
Max Act: 4.5941. Min Act: -0.1700
Data Index: 6148975 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8128. Min Range: -4.8128
Max Act: 4.5628. Min Act: -0.1700
Data Index: 2560482 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8128. Min Range: -4.8128
Max Act: 4.5941. Min Act: -0.1700
Data Index: 223210 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8128. Min Range: -4.8128
Max Act: 4.5628. Min Act: -0.1700
Data Index: 4327303 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19