Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 989 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5479. Min Range: -5.5479
Max Act: 5.5479. Min Act: -0.1700
Data Index: 878606 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5479. Min Range: -5.5479
Max Act: 5.4229. Min Act: -0.1700
Data Index: 7103372 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5479. Min Range: -5.5479
Max Act: 5.2667. Min Act: -0.1700
Data Index: 155318 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5479. Min Range: -5.5479
Max Act: 5.2042. Min Act: -0.1700
Data Index: 1643666 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5479. Min Range: -5.5479
Max Act: 5.1417. Min Act: -0.1700
Data Index: 4593664 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5479. Min Range: -5.5479
Max Act: 5.1417. Min Act: -0.1700
Data Index: 3873491 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5479. Min Range: -5.5479
Max Act: 5.0792. Min Act: -0.1700
Data Index: 6102284 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5479. Min Range: -5.5479
Max Act: 5.0792. Min Act: -0.1700
Data Index: 8433634 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5479. Min Range: -5.5479
Max Act: 5.0792. Min Act: -0.1700
Data Index: 6090361 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5479. Min Range: -5.5479
Max Act: 5.1104. Min Act: -0.1700
Data Index: 4253107 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5479. Min Range: -5.5479
Max Act: 5.0792. Min Act: -0.1700
Data Index: 4673011 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5479. Min Range: -5.5479
Max Act: 5.0167. Min Act: -0.1700
Data Index: 5390857 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5479. Min Range: -5.5479
Max Act: 5.0167. Min Act: -0.1700
Data Index: 1774738 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5479. Min Range: -5.5479
Max Act: 5.0167. Min Act: -0.1700
Data Index: 5683845 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5479. Min Range: -5.5479
Max Act: 5.0167. Min Act: -0.1700
Data Index: 2486899 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5479. Min Range: -5.5479
Max Act: 5.0167. Min Act: -0.1700
Data Index: 8026705 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5479. Min Range: -5.5479
Max Act: 4.9854. Min Act: -0.1700
Data Index: 938637 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5479. Min Range: -5.5479
Max Act: 4.9854. Min Act: -0.1700
Data Index: 7294016 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5479. Min Range: -5.5479
Max Act: 4.9854. Min Act: -0.1700
Data Index: 2900078 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5479. Min Range: -5.5479
Max Act: 4.9854. Min Act: -0.1700
Data Index: 3759010 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19