Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5249 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6590. Min Range: -5.6590
Max Act: 5.6590. Min Act: -0.1700
Data Index: 939509 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6590. Min Range: -5.6590
Max Act: 5.6590. Min Act: -0.1700
Data Index: 6353624 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6590. Min Range: -5.6590
Max Act: 5.6590. Min Act: -0.1700
Data Index: 4354410 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6590. Min Range: -5.6590
Max Act: 5.6277. Min Act: -0.1700
Data Index: 8267998 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6590. Min Range: -5.6590
Max Act: 5.6277. Min Act: -0.1700
Data Index: 4567503 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6590. Min Range: -5.6590
Max Act: 5.5652. Min Act: -0.1700
Data Index: 5140700 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6590. Min Range: -5.6590
Max Act: 5.5965. Min Act: -0.1700
Data Index: 2268282 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6590. Min Range: -5.6590
Max Act: 5.5652. Min Act: -0.1700
Data Index: 5220186 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6590. Min Range: -5.6590
Max Act: 5.5340. Min Act: -0.1700
Data Index: 7489515 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6590. Min Range: -5.6590
Max Act: 5.5340. Min Act: -0.1700
Data Index: 6914315 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6590. Min Range: -5.6590
Max Act: 5.5340. Min Act: -0.1700
Data Index: 5623425 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6590. Min Range: -5.6590
Max Act: 5.5340. Min Act: -0.1700
Data Index: 6155926 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6590. Min Range: -5.6590
Max Act: 5.5027. Min Act: -0.1700
Data Index: 6340329 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6590. Min Range: -5.6590
Max Act: 5.5340. Min Act: -0.1700
Data Index: 5140699 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6590. Min Range: -5.6590
Max Act: 5.5340. Min Act: -0.1700
Data Index: 1640264 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6590. Min Range: -5.6590
Max Act: 5.5340. Min Act: -0.1700
Data Index: 4717219 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6590. Min Range: -5.6590
Max Act: 5.5027. Min Act: -0.1700
Data Index: 162693 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6590. Min Range: -5.6590
Max Act: 5.5027. Min Act: -0.1700
Data Index: 1599251 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6590. Min Range: -5.6590
Max Act: 5.5027. Min Act: -0.1700
Data Index: 4911298 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6590. Min Range: -5.6590
Max Act: 5.5027. Min Act: -0.1700
Data Index: 585564 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19