Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3125 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0830. Min Range: -4.0830
Max Act: 4.0830. Min Act: -0.1700
Data Index: 8269191 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0830. Min Range: -4.0830
Max Act: 4.0517. Min Act: -0.1700
Data Index: 8269190 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0830. Min Range: -4.0830
Max Act: 4.0204. Min Act: -0.1700
Data Index: 2661491 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0830. Min Range: -4.0830
Max Act: 4.0517. Min Act: -0.1700
Data Index: 6809118 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0830. Min Range: -4.0830
Max Act: 4.0204. Min Act: -0.1700
Data Index: 2025128 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0830. Min Range: -4.0830
Max Act: 4.0204. Min Act: -0.1700
Data Index: 4431044 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0830. Min Range: -4.0830
Max Act: 3.9892. Min Act: -0.1700
Data Index: 8447106 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0830. Min Range: -4.0830
Max Act: 3.9579. Min Act: -0.1700
Data Index: 8736932 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0830. Min Range: -4.0830
Max Act: 3.9892. Min Act: -0.1700
Data Index: 1996048 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0830. Min Range: -4.0830
Max Act: 3.9579. Min Act: -0.1700
Data Index: 5919006 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0830. Min Range: -4.0830
Max Act: 3.9579. Min Act: -0.1700
Data Index: 2670929 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0830. Min Range: -4.0830
Max Act: 3.9579. Min Act: -0.1700
Data Index: 978784 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0830. Min Range: -4.0830
Max Act: 3.9579. Min Act: -0.1700
Data Index: 8771315 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0830. Min Range: -4.0830
Max Act: 3.9267. Min Act: -0.1700
Data Index: 3613977 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0830. Min Range: -4.0830
Max Act: 3.9267. Min Act: -0.1700
Data Index: 661399 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0830. Min Range: -4.0830
Max Act: 3.9267. Min Act: -0.1700
Data Index: 2242039 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0830. Min Range: -4.0830
Max Act: 3.9267. Min Act: -0.1700
Data Index: 512524 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0830. Min Range: -4.0830
Max Act: 3.9267. Min Act: -0.1700
Data Index: 362343 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0830. Min Range: -4.0830
Max Act: 3.8954. Min Act: -0.1700
Data Index: 7340477 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0830. Min Range: -4.0830
Max Act: 3.8954. Min Act: -0.1700
Data Index: 196467 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19