Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1862 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5853. Min Range: -5.5853
Max Act: 5.5853. Min Act: -0.1700
Data Index: 1765513 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5853. Min Range: -5.5853
Max Act: 5.5853. Min Act: -0.1700
Data Index: 3194583 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5853. Min Range: -5.5853
Max Act: 5.5228. Min Act: -0.1700
Data Index: 670686 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5853. Min Range: -5.5853
Max Act: 5.4915. Min Act: -0.1700
Data Index: 1748438 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5853. Min Range: -5.5853
Max Act: 5.4290. Min Act: -0.1700
Data Index: 4224650 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5853. Min Range: -5.5853
Max Act: 5.3978. Min Act: -0.1700
Data Index: 249470 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5853. Min Range: -5.5853
Max Act: 5.3665. Min Act: -0.1700
Data Index: 1989459 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5853. Min Range: -5.5853
Max Act: 5.3353. Min Act: -0.1700
Data Index: 8556582 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5853. Min Range: -5.5853
Max Act: 5.3978. Min Act: -0.1700
Data Index: 6913749 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5853. Min Range: -5.5853
Max Act: 5.3353. Min Act: -0.1700
Data Index: 1432227 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5853. Min Range: -5.5853
Max Act: 5.3353. Min Act: -0.1700
Data Index: 4245817 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5853. Min Range: -5.5853
Max Act: 5.3040. Min Act: -0.1700
Data Index: 8593034 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5853. Min Range: -5.5853
Max Act: 5.3040. Min Act: -0.1700
Data Index: 3321036 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5853. Min Range: -5.5853
Max Act: 5.2728. Min Act: -0.1700
Data Index: 6003928 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5853. Min Range: -5.5853
Max Act: 5.2415. Min Act: -0.1700
Data Index: 7452979 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5853. Min Range: -5.5853
Max Act: 5.2415. Min Act: -0.1700
Data Index: 726613 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5853. Min Range: -5.5853
Max Act: 5.2415. Min Act: -0.1700
Data Index: 1860533 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5853. Min Range: -5.5853
Max Act: 5.2415. Min Act: -0.1700
Data Index: 2602868 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5853. Min Range: -5.5853
Max Act: 5.2415. Min Act: -0.1700
Data Index: 2918774 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5853. Min Range: -5.5853
Max Act: 5.2415. Min Act: -0.1700
Data Index: 3563983 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19