Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6378 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0805. Min Range: -6.0805
Max Act: 6.0805. Min Act: -0.1700
Data Index: 4457091 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0805. Min Range: -6.0805
Max Act: 6.0493. Min Act: -0.1700
Data Index: 5108955 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0805. Min Range: -6.0805
Max Act: 6.0493. Min Act: -0.1700
Data Index: 4563421 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.9868. Min Act: -0.1700
Data Index: 972707 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.9868. Min Act: -0.1700
Data Index: 4902553 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.9555. Min Act: -0.1700
Data Index: 169220 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.9555. Min Act: -0.1700
Data Index: 6424118 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.9243. Min Act: -0.1700
Data Index: 4215770 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.8618. Min Act: -0.1700
Data Index: 7589996 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.8305. Min Act: -0.1700
Data Index: 4904392 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.7680. Min Act: -0.1700
Data Index: 2803072 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.7680. Min Act: -0.1700
Data Index: 6905865 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.7680. Min Act: -0.1700
Data Index: 8167473 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.7368. Min Act: -0.1700
Data Index: 4219088 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.6743. Min Act: -0.1700
Data Index: 31033 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.6743. Min Act: -0.1700
Data Index: 4170442 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.6743. Min Act: -0.1700
Data Index: 31037 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.6430. Min Act: -0.1700
Data Index: 2788905 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.6118. Min Act: -0.1700
Data Index: 996578 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0805. Min Range: -6.0805
Max Act: 5.6430. Min Act: -0.1700
Data Index: 8290353 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19