Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3186 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0973. Min Range: -8.0973
Max Act: 8.0973. Min Act: -0.1700
Data Index: 1287713 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0973. Min Range: -8.0973
Max Act: 7.5348. Min Act: -0.1700
Data Index: 2019989 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0973. Min Range: -8.0973
Max Act: 7.4098. Min Act: -0.1700
Data Index: 3779261 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0973. Min Range: -8.0973
Max Act: 7.3161. Min Act: -0.1700
Data Index: 3616142 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0973. Min Range: -8.0973
Max Act: 7.1911. Min Act: -0.1700
Data Index: 4228958 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0973. Min Range: -8.0973
Max Act: 7.1598. Min Act: -0.1700
Data Index: 2399355 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0973. Min Range: -8.0973
Max Act: 7.0973. Min Act: -0.1700
Data Index: 8233428 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0973. Min Range: -8.0973
Max Act: 7.0973. Min Act: -0.1700
Data Index: 8421707 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0973. Min Range: -8.0973
Max Act: 7.0348. Min Act: -0.1700
Data Index: 1220097 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0973. Min Range: -8.0973
Max Act: 7.0348. Min Act: -0.1700
Data Index: 7257471 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0973. Min Range: -8.0973
Max Act: 7.0348. Min Act: -0.1700
Data Index: 8401587 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0973. Min Range: -8.0973
Max Act: 7.0036. Min Act: -0.1700
Data Index: 8579651 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0973. Min Range: -8.0973
Max Act: 6.9723. Min Act: -0.1700
Data Index: 6154765 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0973. Min Range: -8.0973
Max Act: 6.9723. Min Act: -0.1700
Data Index: 1527659 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0973. Min Range: -8.0973
Max Act: 6.9411. Min Act: -0.1700
Data Index: 6530461 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0973. Min Range: -8.0973
Max Act: 6.9723. Min Act: -0.1700
Data Index: 6118615 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0973. Min Range: -8.0973
Max Act: 6.9411. Min Act: -0.1700
Data Index: 3227913 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0973. Min Range: -8.0973
Max Act: 6.9098. Min Act: -0.1700
Data Index: 6159144 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0973. Min Range: -8.0973
Max Act: 6.9098. Min Act: -0.1700
Data Index: 1499875 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0973. Min Range: -8.0973
Max Act: 6.8473. Min Act: -0.1700
Data Index: 2785584 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19