Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3805 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.3390. Min Range: -11.3390
Max Act: 11.3390. Min Act: -0.1700
Data Index: 6570349 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3390. Min Range: -11.3390
Max Act: 10.5890. Min Act: -0.1700
Data Index: 5998689 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3390. Min Range: -11.3390
Max Act: 10.4640. Min Act: -0.1700
Data Index: 8056871 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3390. Min Range: -11.3390
Max Act: 10.4015. Min Act: -0.1700
Data Index: 2531363 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3390. Min Range: -11.3390
Max Act: 10.3390. Min Act: -0.1700
Data Index: 5204507 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3390. Min Range: -11.3390
Max Act: 10.1515. Min Act: -0.1700
Data Index: 5488959 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3390. Min Range: -11.3390
Max Act: 10.1515. Min Act: -0.1700
Data Index: 7734399 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3390. Min Range: -11.3390
Max Act: 9.9640. Min Act: -0.1700
Data Index: 3773805 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3390. Min Range: -11.3390
Max Act: 9.9640. Min Act: -0.1700
Data Index: 2858720 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3390. Min Range: -11.3390
Max Act: 9.9640. Min Act: -0.1700
Data Index: 7008536 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3390. Min Range: -11.3390
Max Act: 9.9015. Min Act: -0.1700
Data Index: 2814348 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3390. Min Range: -11.3390
Max Act: 9.8390. Min Act: -0.1700
Data Index: 5488962 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3390. Min Range: -11.3390
Max Act: 9.8390. Min Act: -0.1700
Data Index: 6150370 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3390. Min Range: -11.3390
Max Act: 9.7765. Min Act: -0.1700
Data Index: 666919 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3390. Min Range: -11.3390
Max Act: 9.7765. Min Act: -0.1700
Data Index: 8276407 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3390. Min Range: -11.3390
Max Act: 9.7140. Min Act: -0.1700
Data Index: 3118895 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3390. Min Range: -11.3390
Max Act: 9.7140. Min Act: -0.1700
Data Index: 823717 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3390. Min Range: -11.3390
Max Act: 9.7140. Min Act: -0.1700
Data Index: 2853862 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3390. Min Range: -11.3390
Max Act: 9.6515. Min Act: -0.1700
Data Index: 6225498 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3390. Min Range: -11.3390
Max Act: 9.7140. Min Act: -0.1700
Data Index: 2226692 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #19