Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5584 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.3868. Min Act: -0.1700
Data Index: 5927728 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2930. Min Act: -0.1700
Data Index: 5887147 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2930. Min Act: -0.1700
Data Index: 3621209 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2930. Min Act: -0.1700
Data Index: 8333578 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2930. Min Act: -0.1700
Data Index: 4492504 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2618. Min Act: -0.1700
Data Index: 3374337 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2618. Min Act: -0.1700
Data Index: 5851878 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2305. Min Act: -0.1700
Data Index: 5161987 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2305. Min Act: -0.1700
Data Index: 3259767 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2305. Min Act: -0.1700
Data Index: 6882606 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.2305. Min Act: -0.1700
Data Index: 3409986 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.1993. Min Act: -0.1700
Data Index: 2746147 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.1993. Min Act: -0.1700
Data Index: 1899009 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.1680. Min Act: -0.1700
Data Index: 3061273 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.1680. Min Act: -0.1700
Data Index: 3055695 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.1680. Min Act: -0.1700
Data Index: 2804154 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.1680. Min Act: -0.1700
Data Index: 8009753 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.1680. Min Act: -0.1700
Data Index: 7683878 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.1367. Min Act: -0.1700
Data Index: 893435 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3868. Min Range: -4.3868
Max Act: 4.1680. Min Act: -0.1700
Data Index: 3668096 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19