Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4747 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9322. Min Range: -7.9322
Max Act: 7.9322. Min Act: -0.1700
Data Index: 7589828 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9322. Min Range: -7.9322
Max Act: 7.4947. Min Act: -0.1700
Data Index: 3499745 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9322. Min Range: -7.9322
Max Act: 7.2447. Min Act: -0.1700
Data Index: 5444357 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9322. Min Range: -7.9322
Max Act: 7.1822. Min Act: -0.1700
Data Index: 4880418 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9322. Min Range: -7.9322
Max Act: 7.1822. Min Act: -0.1700
Data Index: 6479794 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9322. Min Range: -7.9322
Max Act: 7.1822. Min Act: -0.1700
Data Index: 6225791 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9322. Min Range: -7.9322
Max Act: 7.0885. Min Act: -0.1700
Data Index: 3242996 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9322. Min Range: -7.9322
Max Act: 7.0572. Min Act: -0.1700
Data Index: 7553101 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9322. Min Range: -7.9322
Max Act: 7.0572. Min Act: -0.1700
Data Index: 5451574 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9322. Min Range: -7.9322
Max Act: 7.0260. Min Act: -0.1700
Data Index: 1767544 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9322. Min Range: -7.9322
Max Act: 7.0572. Min Act: -0.1700
Data Index: 5030486 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9322. Min Range: -7.9322
Max Act: 7.0260. Min Act: -0.1700
Data Index: 5348924 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9322. Min Range: -7.9322
Max Act: 7.0572. Min Act: -0.1700
Data Index: 4149596 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9322. Min Range: -7.9322
Max Act: 7.0260. Min Act: -0.1700
Data Index: 7887447 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9322. Min Range: -7.9322
Max Act: 7.0260. Min Act: -0.1700
Data Index: 1175021 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9322. Min Range: -7.9322
Max Act: 6.9947. Min Act: -0.1700
Data Index: 6914950 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9322. Min Range: -7.9322
Max Act: 6.9947. Min Act: -0.1700
Data Index: 6140905 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9322. Min Range: -7.9322
Max Act: 6.9947. Min Act: -0.1700
Data Index: 1491472 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9322. Min Range: -7.9322
Max Act: 6.9947. Min Act: -0.1700
Data Index: 7213240 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9322. Min Range: -7.9322
Max Act: 6.9322. Min Act: -0.1700
Data Index: 6163783 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19