Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3612 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6684. Min Range: -2.6684
Max Act: 2.6684. Min Act: -0.1700
Data Index: 5958076 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6684. Min Range: -2.6684
Max Act: 2.6203. Min Act: -0.1700
Data Index: 1285708 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6684. Min Range: -2.6684
Max Act: 2.6203. Min Act: -0.1700
Data Index: 7836752 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6684. Min Range: -2.6684
Max Act: 2.6042. Min Act: -0.1700
Data Index: 7872750 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6684. Min Range: -2.6684
Max Act: 2.6042. Min Act: -0.1700
Data Index: 3845245 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6684. Min Range: -2.6684
Max Act: 2.5881. Min Act: -0.1700
Data Index: 8780285 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6684. Min Range: -2.6684
Max Act: 2.5881. Min Act: -0.1700
Data Index: 5376093 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6684. Min Range: -2.6684
Max Act: 2.5720. Min Act: -0.1700
Data Index: 5623998 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6684. Min Range: -2.6684
Max Act: 2.5559. Min Act: -0.1700
Data Index: 3115188 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6684. Min Range: -2.6684
Max Act: 2.5559. Min Act: -0.1700
Data Index: 8619691 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6684. Min Range: -2.6684
Max Act: 2.5235. Min Act: -0.1700
Data Index: 735712 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6684. Min Range: -2.6684
Max Act: 2.5397. Min Act: -0.1700
Data Index: 7595557 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6684. Min Range: -2.6684
Max Act: 2.5235. Min Act: -0.1700
Data Index: 8734951 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6684. Min Range: -2.6684
Max Act: 2.5235. Min Act: -0.1700
Data Index: 4523596 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6684. Min Range: -2.6684
Max Act: 2.5074. Min Act: -0.1700
Data Index: 534432 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6684. Min Range: -2.6684
Max Act: 2.5235. Min Act: -0.1700
Data Index: 6785703 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6684. Min Range: -2.6684
Max Act: 2.5235. Min Act: -0.1700
Data Index: 5614314 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6684. Min Range: -2.6684
Max Act: 2.5074. Min Act: -0.1700
Data Index: 2080653 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6684. Min Range: -2.6684
Max Act: 2.5074. Min Act: -0.1700
Data Index: 2109984 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6684. Min Range: -2.6684
Max Act: 2.5074. Min Act: -0.1700
Data Index: 468574 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19