Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3610 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9281. Min Range: -9.9281
Max Act: 9.9281. Min Act: -0.1700
Data Index: 195248 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9281. Min Range: -9.9281
Max Act: 9.5531. Min Act: -0.1700
Data Index: 6492982 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9281. Min Range: -9.9281
Max Act: 9.4906. Min Act: -0.1700
Data Index: 7774983 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9281. Min Range: -9.9281
Max Act: 9.2406. Min Act: -0.1700
Data Index: 144346 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9281. Min Range: -9.9281
Max Act: 9.1156. Min Act: -0.1700
Data Index: 5832526 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9281. Min Range: -9.9281
Max Act: 9.0531. Min Act: -0.1700
Data Index: 5781643 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9281. Min Range: -9.9281
Max Act: 8.8656. Min Act: -0.1700
Data Index: 7884779 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9281. Min Range: -9.9281
Max Act: 8.9281. Min Act: -0.1700
Data Index: 1401569 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9281. Min Range: -9.9281
Max Act: 8.8656. Min Act: -0.1700
Data Index: 183532 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9281. Min Range: -9.9281
Max Act: 8.8656. Min Act: -0.1700
Data Index: 4075748 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9281. Min Range: -9.9281
Max Act: 8.8656. Min Act: -0.1700
Data Index: 3110533 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9281. Min Range: -9.9281
Max Act: 8.8656. Min Act: -0.1700
Data Index: 4833502 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9281. Min Range: -9.9281
Max Act: 8.8031. Min Act: -0.1700
Data Index: 4857026 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9281. Min Range: -9.9281
Max Act: 8.8031. Min Act: -0.1700
Data Index: 2142848 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9281. Min Range: -9.9281
Max Act: 8.8031. Min Act: -0.1700
Data Index: 408295 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9281. Min Range: -9.9281
Max Act: 8.8031. Min Act: -0.1700
Data Index: 1254523 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9281. Min Range: -9.9281
Max Act: 8.8031. Min Act: -0.1700
Data Index: 8345872 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9281. Min Range: -9.9281
Max Act: 8.7406. Min Act: -0.1700
Data Index: 7130177 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9281. Min Range: -9.9281
Max Act: 8.7406. Min Act: -0.1700
Data Index: 3624717 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9281. Min Range: -9.9281
Max Act: 8.7406. Min Act: -0.1700
Data Index: 7509536 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19