Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3299 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1935. Min Range: -7.1935
Max Act: 7.1935. Min Act: -0.1700
Data Index: 5160783 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1935. Min Range: -7.1935
Max Act: 7.0997. Min Act: -0.1700
Data Index: 6709702 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1935. Min Range: -7.1935
Max Act: 6.9122. Min Act: -0.1700
Data Index: 6418641 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1935. Min Range: -7.1935
Max Act: 6.7872. Min Act: -0.1700
Data Index: 6807215 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1935. Min Range: -7.1935
Max Act: 6.7560. Min Act: -0.1700
Data Index: 4662440 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1935. Min Range: -7.1935
Max Act: 6.7247. Min Act: -0.1700
Data Index: 6722514 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1935. Min Range: -7.1935
Max Act: 6.7247. Min Act: -0.1700
Data Index: 4790805 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1935. Min Range: -7.1935
Max Act: 6.7247. Min Act: -0.1700
Data Index: 3903724 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1935. Min Range: -7.1935
Max Act: 6.6622. Min Act: -0.1700
Data Index: 4955078 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1935. Min Range: -7.1935
Max Act: 6.6622. Min Act: -0.1700
Data Index: 4516577 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1935. Min Range: -7.1935
Max Act: 6.6310. Min Act: -0.1700
Data Index: 4194521 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1935. Min Range: -7.1935
Max Act: 6.6310. Min Act: -0.1700
Data Index: 468207 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1935. Min Range: -7.1935
Max Act: 6.5997. Min Act: -0.1700
Data Index: 2477767 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1935. Min Range: -7.1935
Max Act: 6.5372. Min Act: -0.1700
Data Index: 6313563 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1935. Min Range: -7.1935
Max Act: 6.5997. Min Act: -0.1700
Data Index: 5206520 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1935. Min Range: -7.1935
Max Act: 6.5685. Min Act: -0.1700
Data Index: 2799854 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1935. Min Range: -7.1935
Max Act: 6.5685. Min Act: -0.1700
Data Index: 742020 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1935. Min Range: -7.1935
Max Act: 6.5372. Min Act: -0.1700
Data Index: 800985 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1935. Min Range: -7.1935
Max Act: 6.4747. Min Act: -0.1700
Data Index: 6876567 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1935. Min Range: -7.1935
Max Act: 6.5060. Min Act: -0.1700
Data Index: 3618168 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19