Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2873 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5100. Min Range: -8.5100
Max Act: 8.5100. Min Act: -0.1700
Data Index: 677669 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5100. Min Range: -8.5100
Max Act: 8.0725. Min Act: -0.1700
Data Index: 2575009 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5100. Min Range: -8.5100
Max Act: 7.9475. Min Act: -0.1700
Data Index: 6930684 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5100. Min Range: -8.5100
Max Act: 7.8225. Min Act: -0.1700
Data Index: 36329 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5100. Min Range: -8.5100
Max Act: 7.8225. Min Act: -0.1700
Data Index: 7035565 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5100. Min Range: -8.5100
Max Act: 7.6975. Min Act: -0.1700
Data Index: 7113012 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5100. Min Range: -8.5100
Max Act: 7.6350. Min Act: -0.1700
Data Index: 6862630 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5100. Min Range: -8.5100
Max Act: 7.6350. Min Act: -0.1700
Data Index: 2079974 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5100. Min Range: -8.5100
Max Act: 7.6350. Min Act: -0.1700
Data Index: 639559 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5100. Min Range: -8.5100
Max Act: 7.5725. Min Act: -0.1700
Data Index: 5301274 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5100. Min Range: -8.5100
Max Act: 7.5725. Min Act: -0.1700
Data Index: 4998842 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5100. Min Range: -8.5100
Max Act: 7.5725. Min Act: -0.1700
Data Index: 1830031 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5100. Min Range: -8.5100
Max Act: 7.5725. Min Act: -0.1700
Data Index: 544398 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5100. Min Range: -8.5100
Max Act: 7.5100. Min Act: -0.1700
Data Index: 5227554 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5100. Min Range: -8.5100
Max Act: 7.5100. Min Act: -0.1700
Data Index: 1418721 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5100. Min Range: -8.5100
Max Act: 7.5100. Min Act: -0.1700
Data Index: 1148774 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5100. Min Range: -8.5100
Max Act: 7.4788. Min Act: -0.1700
Data Index: 8146245 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5100. Min Range: -8.5100
Max Act: 7.2600. Min Act: -0.1700
Data Index: 688342 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5100. Min Range: -8.5100
Max Act: 7.2913. Min Act: -0.1700
Data Index: 4852187 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5100. Min Range: -8.5100
Max Act: 7.2913. Min Act: -0.1700
Data Index: 5077525 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19