Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2848 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4563. Min Range: -8.4563
Max Act: 8.4563. Min Act: -0.1700
Data Index: 269832 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4563. Min Range: -8.4563
Max Act: 7.7688. Min Act: -0.1700
Data Index: 5324763 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4563. Min Range: -8.4563
Max Act: 7.7063. Min Act: -0.1700
Data Index: 3499826 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4563. Min Range: -8.4563
Max Act: 7.4563. Min Act: -0.1700
Data Index: 7392050 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4563. Min Range: -8.4563
Max Act: 7.3626. Min Act: -0.1700
Data Index: 2751762 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4563. Min Range: -8.4563
Max Act: 7.3313. Min Act: -0.1700
Data Index: 190072 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4563. Min Range: -8.4563
Max Act: 7.3001. Min Act: -0.1700
Data Index: 1680718 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4563. Min Range: -8.4563
Max Act: 7.2688. Min Act: -0.1700
Data Index: 53371 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4563. Min Range: -8.4563
Max Act: 7.2063. Min Act: -0.1700
Data Index: 1529284 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4563. Min Range: -8.4563
Max Act: 7.2688. Min Act: -0.1700
Data Index: 5483656 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4563. Min Range: -8.4563
Max Act: 7.2376. Min Act: -0.1700
Data Index: 521034 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4563. Min Range: -8.4563
Max Act: 7.2376. Min Act: -0.1700
Data Index: 6649966 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4563. Min Range: -8.4563
Max Act: 7.2688. Min Act: -0.1700
Data Index: 564207 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4563. Min Range: -8.4563
Max Act: 7.2063. Min Act: -0.1700
Data Index: 8477926 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4563. Min Range: -8.4563
Max Act: 7.2063. Min Act: -0.1700
Data Index: 4047956 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4563. Min Range: -8.4563
Max Act: 7.2063. Min Act: -0.1700
Data Index: 7048978 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4563. Min Range: -8.4563
Max Act: 7.1438. Min Act: -0.1700
Data Index: 1855886 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4563. Min Range: -8.4563
Max Act: 7.1438. Min Act: -0.1700
Data Index: 6185078 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4563. Min Range: -8.4563
Max Act: 7.1438. Min Act: -0.1700
Data Index: 4612693 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4563. Min Range: -8.4563
Max Act: 7.1751. Min Act: -0.1700
Data Index: 4283991 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19