Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4913 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5977. Min Range: -7.5977
Max Act: 7.5977. Min Act: -0.1700
Data Index: 4070735 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5977. Min Range: -7.5977
Max Act: 7.4727. Min Act: -0.1700
Data Index: 3693471 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5977. Min Range: -7.5977
Max Act: 7.4727. Min Act: -0.1700
Data Index: 66872 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5977. Min Range: -7.5977
Max Act: 7.4102. Min Act: -0.1700
Data Index: 7194957 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5977. Min Range: -7.5977
Max Act: 7.3477. Min Act: -0.1700
Data Index: 4512003 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5977. Min Range: -7.5977
Max Act: 7.2852. Min Act: -0.1700
Data Index: 1386900 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5977. Min Range: -7.5977
Max Act: 7.2540. Min Act: -0.1700
Data Index: 2919763 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5977. Min Range: -7.5977
Max Act: 7.2540. Min Act: -0.1700
Data Index: 7744906 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5977. Min Range: -7.5977
Max Act: 7.2227. Min Act: -0.1700
Data Index: 499490 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5977. Min Range: -7.5977
Max Act: 7.1915. Min Act: -0.1700
Data Index: 6985862 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5977. Min Range: -7.5977
Max Act: 7.1602. Min Act: -0.1700
Data Index: 1790885 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5977. Min Range: -7.5977
Max Act: 7.1602. Min Act: -0.1700
Data Index: 428456 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5977. Min Range: -7.5977
Max Act: 7.1290. Min Act: -0.1700
Data Index: 597957 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5977. Min Range: -7.5977
Max Act: 7.1290. Min Act: -0.1700
Data Index: 8667957 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5977. Min Range: -7.5977
Max Act: 7.1290. Min Act: -0.1700
Data Index: 5697337 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5977. Min Range: -7.5977
Max Act: 7.0977. Min Act: -0.1700
Data Index: 3962662 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5977. Min Range: -7.5977
Max Act: 7.0977. Min Act: -0.1700
Data Index: 8297174 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5977. Min Range: -7.5977
Max Act: 7.1290. Min Act: -0.1700
Data Index: 1666911 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5977. Min Range: -7.5977
Max Act: 7.1290. Min Act: -0.1700
Data Index: 985886 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5977. Min Range: -7.5977
Max Act: 7.0665. Min Act: -0.1700
Data Index: 6618655 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19