Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4889 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6072. Min Range: -8.6072
Max Act: 8.6072. Min Act: -0.1700
Data Index: 1040672 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6072. Min Range: -8.6072
Max Act: 8.6072. Min Act: -0.1700
Data Index: 3126184 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6072. Min Range: -8.6072
Max Act: 8.5447. Min Act: -0.1700
Data Index: 3341844 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6072. Min Range: -8.6072
Max Act: 8.4822. Min Act: -0.1700
Data Index: 263412 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6072. Min Range: -8.6072
Max Act: 8.4822. Min Act: -0.1700
Data Index: 8193023 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6072. Min Range: -8.6072
Max Act: 8.3572. Min Act: -0.1700
Data Index: 3886314 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6072. Min Range: -8.6072
Max Act: 8.3572. Min Act: -0.1700
Data Index: 6505791 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6072. Min Range: -8.6072
Max Act: 8.3572. Min Act: -0.1700
Data Index: 7982699 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6072. Min Range: -8.6072
Max Act: 8.2947. Min Act: -0.1700
Data Index: 8610963 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6072. Min Range: -8.6072
Max Act: 8.2947. Min Act: -0.1700
Data Index: 6341791 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6072. Min Range: -8.6072
Max Act: 8.2947. Min Act: -0.1700
Data Index: 3263521 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6072. Min Range: -8.6072
Max Act: 8.2322. Min Act: -0.1700
Data Index: 5979516 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6072. Min Range: -8.6072
Max Act: 8.2322. Min Act: -0.1700
Data Index: 6037207 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6072. Min Range: -8.6072
Max Act: 8.2322. Min Act: -0.1700
Data Index: 6484279 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6072. Min Range: -8.6072
Max Act: 8.1697. Min Act: -0.1700
Data Index: 4121012 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6072. Min Range: -8.6072
Max Act: 8.1697. Min Act: -0.1700
Data Index: 4924974 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6072. Min Range: -8.6072
Max Act: 8.1072. Min Act: -0.1700
Data Index: 8424994 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6072. Min Range: -8.6072
Max Act: 8.1072. Min Act: -0.1700
Data Index: 1315566 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6072. Min Range: -8.6072
Max Act: 8.1072. Min Act: -0.1700
Data Index: 636235 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6072. Min Range: -8.6072
Max Act: 8.1072. Min Act: -0.1700
Data Index: 3903737 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19