Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3652 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7704. Min Range: -6.7704
Max Act: 6.7704. Min Act: -0.1700
Data Index: 6296049 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7704. Min Range: -6.7704
Max Act: 6.7391. Min Act: -0.1700
Data Index: 1941353 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7704. Min Range: -6.7704
Max Act: 6.7079. Min Act: -0.1700
Data Index: 4611486 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7704. Min Range: -6.7704
Max Act: 6.6454. Min Act: -0.1700
Data Index: 4913472 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7704. Min Range: -6.7704
Max Act: 6.6766. Min Act: -0.1700
Data Index: 4540505 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7704. Min Range: -6.7704
Max Act: 6.6454. Min Act: -0.1700
Data Index: 6951144 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7704. Min Range: -6.7704
Max Act: 6.6141. Min Act: -0.1700
Data Index: 2236295 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7704. Min Range: -6.7704
Max Act: 6.5829. Min Act: -0.1700
Data Index: 8702477 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7704. Min Range: -6.7704
Max Act: 6.6141. Min Act: -0.1700
Data Index: 3676899 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7704. Min Range: -6.7704
Max Act: 6.6141. Min Act: -0.1700
Data Index: 7270616 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7704. Min Range: -6.7704
Max Act: 6.6141. Min Act: -0.1700
Data Index: 5476169 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7704. Min Range: -6.7704
Max Act: 6.5829. Min Act: -0.1700
Data Index: 2000067 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7704. Min Range: -6.7704
Max Act: 6.4891. Min Act: -0.1700
Data Index: 3083665 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7704. Min Range: -6.7704
Max Act: 6.5204. Min Act: -0.1700
Data Index: 1105442 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7704. Min Range: -6.7704
Max Act: 6.4579. Min Act: -0.1700
Data Index: 8572103 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7704. Min Range: -6.7704
Max Act: 6.4579. Min Act: -0.1700
Data Index: 523698 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7704. Min Range: -6.7704
Max Act: 6.4891. Min Act: -0.1700
Data Index: 8234685 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7704. Min Range: -6.7704
Max Act: 6.4579. Min Act: -0.1700
Data Index: 5588824 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7704. Min Range: -6.7704
Max Act: 6.4579. Min Act: -0.1700
Data Index: 6109568 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7704. Min Range: -6.7704
Max Act: 6.4266. Min Act: -0.1700
Data Index: 5341109 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19