Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3491 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8834. Min Range: -5.8834
Max Act: 5.8834. Min Act: -0.1700
Data Index: 4860431 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8834. Min Range: -5.8834
Max Act: 5.8209. Min Act: -0.1700
Data Index: 5972471 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8834. Min Range: -5.8834
Max Act: 5.7897. Min Act: -0.1700
Data Index: 1659478 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8834. Min Range: -5.8834
Max Act: 5.7272. Min Act: -0.1700
Data Index: 8673876 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8834. Min Range: -5.8834
Max Act: 5.6959. Min Act: -0.1700
Data Index: 38904 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8834. Min Range: -5.8834
Max Act: 5.7272. Min Act: -0.1700
Data Index: 332379 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8834. Min Range: -5.8834
Max Act: 5.6647. Min Act: -0.1700
Data Index: 2708215 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8834. Min Range: -5.8834
Max Act: 5.6959. Min Act: -0.1700
Data Index: 1363184 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8834. Min Range: -5.8834
Max Act: 5.6647. Min Act: -0.1700
Data Index: 2597121 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8834. Min Range: -5.8834
Max Act: 5.6647. Min Act: -0.1700
Data Index: 5524203 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8834. Min Range: -5.8834
Max Act: 5.6334. Min Act: -0.1700
Data Index: 4930526 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8834. Min Range: -5.8834
Max Act: 5.6022. Min Act: -0.1700
Data Index: 7304518 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8834. Min Range: -5.8834
Max Act: 5.6647. Min Act: -0.1700
Data Index: 8160128 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8834. Min Range: -5.8834
Max Act: 5.6334. Min Act: -0.1700
Data Index: 8210062 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8834. Min Range: -5.8834
Max Act: 5.6334. Min Act: -0.1700
Data Index: 8370814 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8834. Min Range: -5.8834
Max Act: 5.6334. Min Act: -0.1700
Data Index: 2937839 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8834. Min Range: -5.8834
Max Act: 5.6334. Min Act: -0.1700
Data Index: 7012157 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8834. Min Range: -5.8834
Max Act: 5.6022. Min Act: -0.1700
Data Index: 4587214 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8834. Min Range: -5.8834
Max Act: 5.6022. Min Act: -0.1700
Data Index: 3510106 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8834. Min Range: -5.8834
Max Act: 5.6022. Min Act: -0.1700
Data Index: 3111476 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19