Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1983 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5238. Min Range: -6.5238
Max Act: 6.5238. Min Act: -0.1700
Data Index: 5444087 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5238. Min Range: -6.5238
Max Act: 6.5238. Min Act: -0.1700
Data Index: 1211910 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5238. Min Range: -6.5238
Max Act: 6.4926. Min Act: -0.1700
Data Index: 7710922 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5238. Min Range: -6.5238
Max Act: 6.3988. Min Act: -0.1700
Data Index: 6129123 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5238. Min Range: -6.5238
Max Act: 6.3676. Min Act: -0.1700
Data Index: 6570084 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5238. Min Range: -6.5238
Max Act: 6.3676. Min Act: -0.1700
Data Index: 122487 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5238. Min Range: -6.5238
Max Act: 6.3363. Min Act: -0.1700
Data Index: 1893359 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5238. Min Range: -6.5238
Max Act: 6.3363. Min Act: -0.1700
Data Index: 6713155 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5238. Min Range: -6.5238
Max Act: 6.3363. Min Act: -0.1700
Data Index: 7797609 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5238. Min Range: -6.5238
Max Act: 6.3051. Min Act: -0.1700
Data Index: 5689522 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5238. Min Range: -6.5238
Max Act: 6.3051. Min Act: -0.1700
Data Index: 6741440 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5238. Min Range: -6.5238
Max Act: 6.2738. Min Act: -0.1700
Data Index: 1827138 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5238. Min Range: -6.5238
Max Act: 6.3051. Min Act: -0.1700
Data Index: 1617517 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5238. Min Range: -6.5238
Max Act: 6.2738. Min Act: -0.1700
Data Index: 523851 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5238. Min Range: -6.5238
Max Act: 6.2426. Min Act: -0.1700
Data Index: 7137716 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5238. Min Range: -6.5238
Max Act: 6.2738. Min Act: -0.1700
Data Index: 7528641 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5238. Min Range: -6.5238
Max Act: 6.2738. Min Act: -0.1700
Data Index: 3269812 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5238. Min Range: -6.5238
Max Act: 6.2738. Min Act: -0.1700
Data Index: 3158047 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5238. Min Range: -6.5238
Max Act: 6.2426. Min Act: -0.1700
Data Index: 5929860 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5238. Min Range: -6.5238
Max Act: 6.2426. Min Act: -0.1700
Data Index: 7168167 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19