Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2024 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9479. Min Range: -3.9479
Max Act: 3.9479. Min Act: -0.1700
Data Index: 3715265 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9479. Min Range: -3.9479
Max Act: 3.9323. Min Act: -0.1700
Data Index: 7754966 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9479. Min Range: -3.9479
Max Act: 3.9167. Min Act: -0.1700
Data Index: 5402683 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9479. Min Range: -3.9479
Max Act: 3.9010. Min Act: -0.1700
Data Index: 442284 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9479. Min Range: -3.9479
Max Act: 3.9010. Min Act: -0.1700
Data Index: 2899224 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9479. Min Range: -3.9479
Max Act: 3.8854. Min Act: -0.1700
Data Index: 8370934 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9479. Min Range: -3.9479
Max Act: 3.8385. Min Act: -0.1700
Data Index: 6180707 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9479. Min Range: -3.9479
Max Act: 3.8385. Min Act: -0.1700
Data Index: 993131 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9479. Min Range: -3.9479
Max Act: 3.8385. Min Act: -0.1700
Data Index: 5450413 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9479. Min Range: -3.9479
Max Act: 3.8228. Min Act: -0.1700
Data Index: 6772099 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9479. Min Range: -3.9479
Max Act: 3.8228. Min Act: -0.1700
Data Index: 1896279 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9479. Min Range: -3.9479
Max Act: 3.7916. Min Act: -0.1700
Data Index: 476927 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9479. Min Range: -3.9479
Max Act: 3.7759. Min Act: -0.1700
Data Index: 4594881 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9479. Min Range: -3.9479
Max Act: 3.7759. Min Act: -0.1700
Data Index: 553440 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9479. Min Range: -3.9479
Max Act: 3.7603. Min Act: -0.1700
Data Index: 5150493 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9479. Min Range: -3.9479
Max Act: 3.7603. Min Act: -0.1700
Data Index: 5998508 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9479. Min Range: -3.9479
Max Act: 3.7603. Min Act: -0.1700
Data Index: 8589859 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9479. Min Range: -3.9479
Max Act: 3.7603. Min Act: -0.1700
Data Index: 4692783 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9479. Min Range: -3.9479
Max Act: 3.7447. Min Act: -0.1700
Data Index: 1829111 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9479. Min Range: -3.9479
Max Act: 3.7134. Min Act: -0.1700
Data Index: 5579180 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19