Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1870 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4328. Min Range: -8.4328
Max Act: 8.4328. Min Act: -0.1700
Data Index: 8310460 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4328. Min Range: -8.4328
Max Act: 8.2453. Min Act: -0.1700
Data Index: 3056784 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4328. Min Range: -8.4328
Max Act: 8.3078. Min Act: -0.1700
Data Index: 6245348 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4328. Min Range: -8.4328
Max Act: 8.0578. Min Act: -0.1700
Data Index: 6471768 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4328. Min Range: -8.4328
Max Act: 7.9953. Min Act: -0.1700
Data Index: 6226462 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4328. Min Range: -8.4328
Max Act: 7.7453. Min Act: -0.1700
Data Index: 7754699 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4328. Min Range: -8.4328
Max Act: 7.6515. Min Act: -0.1700
Data Index: 4186222 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4328. Min Range: -8.4328
Max Act: 7.6828. Min Act: -0.1700
Data Index: 8512424 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4328. Min Range: -8.4328
Max Act: 7.7140. Min Act: -0.1700
Data Index: 6368557 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4328. Min Range: -8.4328
Max Act: 7.5890. Min Act: -0.1700
Data Index: 4270049 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4328. Min Range: -8.4328
Max Act: 7.5890. Min Act: -0.1700
Data Index: 6345690 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4328. Min Range: -8.4328
Max Act: 7.6515. Min Act: -0.1700
Data Index: 795354 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4328. Min Range: -8.4328
Max Act: 7.5890. Min Act: -0.1700
Data Index: 8142255 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4328. Min Range: -8.4328
Max Act: 7.6203. Min Act: -0.1700
Data Index: 5749072 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4328. Min Range: -8.4328
Max Act: 7.5890. Min Act: -0.1700
Data Index: 8666587 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4328. Min Range: -8.4328
Max Act: 7.5578. Min Act: -0.1700
Data Index: 7498863 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4328. Min Range: -8.4328
Max Act: 7.5265. Min Act: -0.1700
Data Index: 6269878 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4328. Min Range: -8.4328
Max Act: 7.4640. Min Act: -0.1700
Data Index: 412969 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4328. Min Range: -8.4328
Max Act: 7.5265. Min Act: -0.1700
Data Index: 7280991 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4328. Min Range: -8.4328
Max Act: 7.4953. Min Act: -0.1700
Data Index: 8806876 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19