Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4507 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6834. Min Range: -4.6834
Max Act: 4.6834. Min Act: -0.1700
Data Index: 2109825 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6834. Min Range: -4.6834
Max Act: 4.5897. Min Act: -0.1700
Data Index: 4107262 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6834. Min Range: -4.6834
Max Act: 4.5897. Min Act: -0.1700
Data Index: 3341113 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6834. Min Range: -4.6834
Max Act: 4.5897. Min Act: -0.1700
Data Index: 8122843 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6834. Min Range: -4.6834
Max Act: 4.5272. Min Act: -0.1700
Data Index: 1818692 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6834. Min Range: -4.6834
Max Act: 4.5272. Min Act: -0.1700
Data Index: 3037712 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6834. Min Range: -4.6834
Max Act: 4.5584. Min Act: -0.1700
Data Index: 3871685 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6834. Min Range: -4.6834
Max Act: 4.4959. Min Act: -0.1700
Data Index: 905029 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6834. Min Range: -4.6834
Max Act: 4.4959. Min Act: -0.1700
Data Index: 642689 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6834. Min Range: -4.6834
Max Act: 4.4959. Min Act: -0.1700
Data Index: 8098962 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6834. Min Range: -4.6834
Max Act: 4.4647. Min Act: -0.1700
Data Index: 3764281 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6834. Min Range: -4.6834
Max Act: 4.4959. Min Act: -0.1700
Data Index: 6410350 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6834. Min Range: -4.6834
Max Act: 4.4647. Min Act: -0.1700
Data Index: 4178796 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6834. Min Range: -4.6834
Max Act: 4.4647. Min Act: -0.1700
Data Index: 1896744 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6834. Min Range: -4.6834
Max Act: 4.4334. Min Act: -0.1700
Data Index: 7298216 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6834. Min Range: -4.6834
Max Act: 4.4334. Min Act: -0.1700
Data Index: 5555083 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6834. Min Range: -4.6834
Max Act: 4.4334. Min Act: -0.1700
Data Index: 4568650 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6834. Min Range: -4.6834
Max Act: 4.4334. Min Act: -0.1700
Data Index: 2799543 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6834. Min Range: -4.6834
Max Act: 4.4334. Min Act: -0.1700
Data Index: 2085668 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6834. Min Range: -4.6834
Max Act: 4.4334. Min Act: -0.1700
Data Index: 5157177 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19