Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1883 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 18.6188. Min Range: -18.6188
Max Act: 18.6188. Min Act: -0.1700
Data Index: 5142396 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 18.6188. Min Range: -18.6188
Max Act: 18.4938. Min Act: -0.1700
Data Index: 3921898 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 18.6188. Min Range: -18.6188
Max Act: 18.2438. Min Act: -0.1700
Data Index: 4765772 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 18.6188. Min Range: -18.6188
Max Act: 17.9938. Min Act: -0.1700
Data Index: 7773452 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 18.6188. Min Range: -18.6188
Max Act: 18.1188. Min Act: -0.1700
Data Index: 2522681 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 18.6188. Min Range: -18.6188
Max Act: 18.1188. Min Act: -0.1700
Data Index: 4746200 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 18.6188. Min Range: -18.6188
Max Act: 17.9938. Min Act: -0.1700
Data Index: 5550128 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 18.6188. Min Range: -18.6188
Max Act: 17.9938. Min Act: -0.1700
Data Index: 7718977 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 18.6188. Min Range: -18.6188
Max Act: 17.9938. Min Act: -0.1700
Data Index: 6826452 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 18.6188. Min Range: -18.6188
Max Act: 17.8688. Min Act: -0.1700
Data Index: 1761766 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 18.6188. Min Range: -18.6188
Max Act: 17.8688. Min Act: -0.1700
Data Index: 1674280 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 18.6188. Min Range: -18.6188
Max Act: 17.8688. Min Act: -0.1700
Data Index: 5771564 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 18.6188. Min Range: -18.6188
Max Act: 17.8688. Min Act: -0.1700
Data Index: 3080776 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 18.6188. Min Range: -18.6188
Max Act: 17.7438. Min Act: -0.1700
Data Index: 1970982 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 18.6188. Min Range: -18.6188
Max Act: 17.8688. Min Act: -0.1700
Data Index: 5265096 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 18.6188. Min Range: -18.6188
Max Act: 17.8688. Min Act: -0.1700
Data Index: 4363029 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 18.6188. Min Range: -18.6188
Max Act: 17.8688. Min Act: -0.1700
Data Index: 4461039 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 18.6188. Min Range: -18.6188
Max Act: 17.7438. Min Act: -0.1700
Data Index: 7934770 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 18.6188. Min Range: -18.6188
Max Act: 17.8688. Min Act: -0.1700
Data Index: 8127847 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 18.6188. Min Range: -18.6188
Max Act: 17.8688. Min Act: -0.1700
Data Index: 6511157 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19