Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2006 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4366. Min Range: -8.4366
Max Act: 8.4366. Min Act: -0.1700
Data Index: 253935 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4366. Min Range: -8.4366
Max Act: 8.3116. Min Act: -0.1700
Data Index: 7904069 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4366. Min Range: -8.4366
Max Act: 8.2491. Min Act: -0.1700
Data Index: 3102933 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4366. Min Range: -8.4366
Max Act: 8.2491. Min Act: -0.1700
Data Index: 4829652 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4366. Min Range: -8.4366
Max Act: 8.1241. Min Act: -0.1700
Data Index: 8444139 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4366. Min Range: -8.4366
Max Act: 8.0616. Min Act: -0.1700
Data Index: 3986245 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4366. Min Range: -8.4366
Max Act: 7.9991. Min Act: -0.1700
Data Index: 915827 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4366. Min Range: -8.4366
Max Act: 7.9991. Min Act: -0.1700
Data Index: 5988169 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4366. Min Range: -8.4366
Max Act: 7.9991. Min Act: -0.1700
Data Index: 3625197 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4366. Min Range: -8.4366
Max Act: 7.9991. Min Act: -0.1700
Data Index: 1771503 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4366. Min Range: -8.4366
Max Act: 7.9366. Min Act: -0.1700
Data Index: 5804822 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4366. Min Range: -8.4366
Max Act: 7.9366. Min Act: -0.1700
Data Index: 3561407 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4366. Min Range: -8.4366
Max Act: 7.9366. Min Act: -0.1700
Data Index: 40342 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4366. Min Range: -8.4366
Max Act: 7.9366. Min Act: -0.1700
Data Index: 4749445 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4366. Min Range: -8.4366
Max Act: 7.9366. Min Act: -0.1700
Data Index: 60831 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4366. Min Range: -8.4366
Max Act: 7.8741. Min Act: -0.1700
Data Index: 1853294 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4366. Min Range: -8.4366
Max Act: 7.8741. Min Act: -0.1700
Data Index: 6590732 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4366. Min Range: -8.4366
Max Act: 7.8116. Min Act: -0.1700
Data Index: 5313537 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4366. Min Range: -8.4366
Max Act: 7.8116. Min Act: -0.1700
Data Index: 5824396 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4366. Min Range: -8.4366
Max Act: 7.8116. Min Act: -0.1700
Data Index: 2892462 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19