Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1686 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7900. Min Range: -3.7900
Max Act: 3.7900. Min Act: -0.1700
Data Index: 606211 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7900. Min Range: -3.7900
Max Act: 3.7431. Min Act: -0.1700
Data Index: 2922788 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7900. Min Range: -3.7900
Max Act: 3.7274. Min Act: -0.1700
Data Index: 5109634 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7900. Min Range: -3.7900
Max Act: 3.7274. Min Act: -0.1700
Data Index: 4148556 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7900. Min Range: -3.7900
Max Act: 3.6648. Min Act: -0.1700
Data Index: 1757778 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7900. Min Range: -3.7900
Max Act: 3.6492. Min Act: -0.1700
Data Index: 1586206 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7900. Min Range: -3.7900
Max Act: 3.5866. Min Act: -0.1700
Data Index: 7370358 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7900. Min Range: -3.7900
Max Act: 3.5866. Min Act: -0.1700
Data Index: 871146 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7900. Min Range: -3.7900
Max Act: 3.5553. Min Act: -0.1700
Data Index: 2009710 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7900. Min Range: -3.7900
Max Act: 3.5396. Min Act: -0.1700
Data Index: 7765473 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7900. Min Range: -3.7900
Max Act: 3.5396. Min Act: -0.1700
Data Index: 3641207 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7900. Min Range: -3.7900
Max Act: 3.5396. Min Act: -0.1700
Data Index: 4424121 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7900. Min Range: -3.7900
Max Act: 3.5240. Min Act: -0.1700
Data Index: 6864055 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7900. Min Range: -3.7900
Max Act: 3.5240. Min Act: -0.1700
Data Index: 6659627 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7900. Min Range: -3.7900
Max Act: 3.5083. Min Act: -0.1700
Data Index: 7716890 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7900. Min Range: -3.7900
Max Act: 3.5240. Min Act: -0.1700
Data Index: 5436851 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7900. Min Range: -3.7900
Max Act: 3.5240. Min Act: -0.1700
Data Index: 3137777 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7900. Min Range: -3.7900
Max Act: 3.5083. Min Act: -0.1700
Data Index: 7069878 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7900. Min Range: -3.7900
Max Act: 3.5240. Min Act: -0.1700
Data Index: 3741730 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7900. Min Range: -3.7900
Max Act: 3.4926. Min Act: -0.1700
Data Index: 7133890 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19