Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3686 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0743. Min Range: -6.0743
Max Act: 6.0743. Min Act: -0.1700
Data Index: 8592518 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0743. Min Range: -6.0743
Max Act: 6.0118. Min Act: -0.1700
Data Index: 7208601 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0743. Min Range: -6.0743
Max Act: 5.9180. Min Act: -0.1700
Data Index: 4308556 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0743. Min Range: -6.0743
Max Act: 5.8868. Min Act: -0.1700
Data Index: 8426697 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0743. Min Range: -6.0743
Max Act: 5.8555. Min Act: -0.1700
Data Index: 5288348 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0743. Min Range: -6.0743
Max Act: 5.7930. Min Act: -0.1700
Data Index: 2926973 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0743. Min Range: -6.0743
Max Act: 5.7930. Min Act: -0.1700
Data Index: 388836 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0743. Min Range: -6.0743
Max Act: 5.8555. Min Act: -0.1700
Data Index: 1461555 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0743. Min Range: -6.0743
Max Act: 5.8243. Min Act: -0.1700
Data Index: 6539337 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0743. Min Range: -6.0743
Max Act: 5.8243. Min Act: -0.1700
Data Index: 6370704 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0743. Min Range: -6.0743
Max Act: 5.8243. Min Act: -0.1700
Data Index: 8441972 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0743. Min Range: -6.0743
Max Act: 5.8243. Min Act: -0.1700
Data Index: 5612131 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0743. Min Range: -6.0743
Max Act: 5.7930. Min Act: -0.1700
Data Index: 6370284 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0743. Min Range: -6.0743
Max Act: 5.7930. Min Act: -0.1700
Data Index: 7892304 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0743. Min Range: -6.0743
Max Act: 5.7930. Min Act: -0.1700
Data Index: 5861848 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0743. Min Range: -6.0743
Max Act: 5.7930. Min Act: -0.1700
Data Index: 3077211 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0743. Min Range: -6.0743
Max Act: 5.7930. Min Act: -0.1700
Data Index: 7796821 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0743. Min Range: -6.0743
Max Act: 5.7930. Min Act: -0.1700
Data Index: 7282717 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0743. Min Range: -6.0743
Max Act: 5.7618. Min Act: -0.1700
Data Index: 5188234 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0743. Min Range: -6.0743
Max Act: 5.7618. Min Act: -0.1700
Data Index: 5288356 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19