Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2704 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.8640. Min Act: -0.1700
Data Index: 6155448 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.7703. Min Act: -0.1700
Data Index: 4072911 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.6765. Min Act: -0.1700
Data Index: 916365 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.6453. Min Act: -0.1700
Data Index: 6092803 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.6140. Min Act: -0.1700
Data Index: 3295776 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.5828. Min Act: -0.1700
Data Index: 6365626 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.5515. Min Act: -0.1700
Data Index: 1604591 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.5515. Min Act: -0.1700
Data Index: 4535880 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.4265. Min Act: -0.1700
Data Index: 5056194 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.3953. Min Act: -0.1700
Data Index: 331909 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.3640. Min Act: -0.1700
Data Index: 122637 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.3640. Min Act: -0.1700
Data Index: 4623794 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.3328. Min Act: -0.1700
Data Index: 3322983 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.3328. Min Act: -0.1700
Data Index: 7837328 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.3015. Min Act: -0.1700
Data Index: 5643080 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.3015. Min Act: -0.1700
Data Index: 27826 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.3015. Min Act: -0.1700
Data Index: 3571293 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.2703. Min Act: -0.1700
Data Index: 5136864 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.2703. Min Act: -0.1700
Data Index: 1959071 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8640. Min Range: -6.8640
Max Act: 6.2703. Min Act: -0.1700
Data Index: 5874469 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19