Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3096 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4903. Min Range: -6.4903
Max Act: 6.4903. Min Act: -0.1700
Data Index: 1336857 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4903. Min Range: -6.4903
Max Act: 6.4903. Min Act: -0.1700
Data Index: 7754846 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4903. Min Range: -6.4903
Max Act: 6.3028. Min Act: -0.1700
Data Index: 4017404 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4903. Min Range: -6.4903
Max Act: 6.3340. Min Act: -0.1700
Data Index: 4494106 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4903. Min Range: -6.4903
Max Act: 6.1778. Min Act: -0.1700
Data Index: 2512917 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4903. Min Range: -6.4903
Max Act: 6.1153. Min Act: -0.1700
Data Index: 5034138 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4903. Min Range: -6.4903
Max Act: 6.1153. Min Act: -0.1700
Data Index: 6125757 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4903. Min Range: -6.4903
Max Act: 6.0528. Min Act: -0.1700
Data Index: 4747837 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4903. Min Range: -6.4903
Max Act: 6.0528. Min Act: -0.1700
Data Index: 753097 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4903. Min Range: -6.4903
Max Act: 6.0215. Min Act: -0.1700
Data Index: 3537037 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4903. Min Range: -6.4903
Max Act: 5.9903. Min Act: -0.1700
Data Index: 3756542 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4903. Min Range: -6.4903
Max Act: 5.9903. Min Act: -0.1700
Data Index: 8231374 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4903. Min Range: -6.4903
Max Act: 5.9903. Min Act: -0.1700
Data Index: 3396755 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4903. Min Range: -6.4903
Max Act: 5.9903. Min Act: -0.1700
Data Index: 88301 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4903. Min Range: -6.4903
Max Act: 5.9590. Min Act: -0.1700
Data Index: 2743796 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4903. Min Range: -6.4903
Max Act: 5.9278. Min Act: -0.1700
Data Index: 6446323 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4903. Min Range: -6.4903
Max Act: 5.8965. Min Act: -0.1700
Data Index: 6183490 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4903. Min Range: -6.4903
Max Act: 5.8653. Min Act: -0.1700
Data Index: 6496655 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4903. Min Range: -6.4903
Max Act: 5.8340. Min Act: -0.1700
Data Index: 6853272 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4903. Min Range: -6.4903
Max Act: 5.8340. Min Act: -0.1700
Data Index: 4827862 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19