Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3390 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5659. Min Range: -3.5659
Max Act: 3.5659. Min Act: -0.1700
Data Index: 5266113 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5659. Min Range: -3.5659
Max Act: 3.5346. Min Act: -0.1700
Data Index: 5406984 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5659. Min Range: -3.5659
Max Act: 3.5189. Min Act: -0.1700
Data Index: 1671411 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5659. Min Range: -3.5659
Max Act: 3.4876. Min Act: -0.1700
Data Index: 4137524 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5659. Min Range: -3.5659
Max Act: 3.4563. Min Act: -0.1700
Data Index: 1751928 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5659. Min Range: -3.5659
Max Act: 3.4406. Min Act: -0.1700
Data Index: 4024831 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5659. Min Range: -3.5659
Max Act: 3.4406. Min Act: -0.1700
Data Index: 1049923 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5659. Min Range: -3.5659
Max Act: 3.4406. Min Act: -0.1700
Data Index: 5003813 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5659. Min Range: -3.5659
Max Act: 3.4092. Min Act: -0.1700
Data Index: 6017646 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5659. Min Range: -3.5659
Max Act: 3.4092. Min Act: -0.1700
Data Index: 3069775 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5659. Min Range: -3.5659
Max Act: 3.4092. Min Act: -0.1700
Data Index: 2857805 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5659. Min Range: -3.5659
Max Act: 3.4249. Min Act: -0.1700
Data Index: 1436493 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5659. Min Range: -3.5659
Max Act: 3.3936. Min Act: -0.1700
Data Index: 1551227 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5659. Min Range: -3.5659
Max Act: 3.3779. Min Act: -0.1700
Data Index: 5150844 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5659. Min Range: -3.5659
Max Act: 3.3779. Min Act: -0.1700
Data Index: 2796227 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5659. Min Range: -3.5659
Max Act: 3.3622. Min Act: -0.1700
Data Index: 4978039 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5659. Min Range: -3.5659
Max Act: 3.3622. Min Act: -0.1700
Data Index: 3717082 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5659. Min Range: -3.5659
Max Act: 3.3622. Min Act: -0.1700
Data Index: 7876138 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5659. Min Range: -3.5659
Max Act: 3.3936. Min Act: -0.1700
Data Index: 7472579 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5659. Min Range: -3.5659
Max Act: 3.3779. Min Act: -0.1700
Data Index: 4714225 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19