Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6342 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3655. Min Range: -7.3655
Max Act: 7.3655. Min Act: -0.1700
Data Index: 891553 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3655. Min Range: -7.3655
Max Act: 7.2718. Min Act: -0.1700
Data Index: 3072406 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3655. Min Range: -7.3655
Max Act: 7.2093. Min Act: -0.1700
Data Index: 8053824 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3655. Min Range: -7.3655
Max Act: 7.1780. Min Act: -0.1700
Data Index: 4240039 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3655. Min Range: -7.3655
Max Act: 7.1468. Min Act: -0.1700
Data Index: 7011941 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3655. Min Range: -7.3655
Max Act: 7.0530. Min Act: -0.1700
Data Index: 3128057 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3655. Min Range: -7.3655
Max Act: 7.0843. Min Act: -0.1700
Data Index: 8250969 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3655. Min Range: -7.3655
Max Act: 7.0530. Min Act: -0.1700
Data Index: 4731594 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3655. Min Range: -7.3655
Max Act: 7.0530. Min Act: -0.1700
Data Index: 5243007 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3655. Min Range: -7.3655
Max Act: 6.9905. Min Act: -0.1700
Data Index: 2085423 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3655. Min Range: -7.3655
Max Act: 6.9593. Min Act: -0.1700
Data Index: 5551741 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3655. Min Range: -7.3655
Max Act: 6.9593. Min Act: -0.1700
Data Index: 2105915 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3655. Min Range: -7.3655
Max Act: 6.9280. Min Act: -0.1700
Data Index: 7115874 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3655. Min Range: -7.3655
Max Act: 6.9280. Min Act: -0.1700
Data Index: 3940534 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3655. Min Range: -7.3655
Max Act: 6.8655. Min Act: -0.1700
Data Index: 5909398 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3655. Min Range: -7.3655
Max Act: 6.8968. Min Act: -0.1700
Data Index: 1276157 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3655. Min Range: -7.3655
Max Act: 6.8655. Min Act: -0.1700
Data Index: 257892 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3655. Min Range: -7.3655
Max Act: 6.8343. Min Act: -0.1700
Data Index: 4604046 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3655. Min Range: -7.3655
Max Act: 6.8343. Min Act: -0.1700
Data Index: 5958945 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3655. Min Range: -7.3655
Max Act: 6.8343. Min Act: -0.1700
Data Index: 5057182 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19