Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3712 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8435. Min Range: -7.8435
Max Act: 7.8435. Min Act: -0.1700
Data Index: 2989605 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8435. Min Range: -7.8435
Max Act: 7.8435. Min Act: -0.1700
Data Index: 5200355 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8435. Min Range: -7.8435
Max Act: 7.6872. Min Act: -0.1700
Data Index: 5672912 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8435. Min Range: -7.8435
Max Act: 7.6247. Min Act: -0.1700
Data Index: 5715373 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8435. Min Range: -7.8435
Max Act: 7.5310. Min Act: -0.1700
Data Index: 1076268 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8435. Min Range: -7.8435
Max Act: 7.5310. Min Act: -0.1700
Data Index: 1281131 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8435. Min Range: -7.8435
Max Act: 7.4997. Min Act: -0.1700
Data Index: 6846787 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8435. Min Range: -7.8435
Max Act: 7.4060. Min Act: -0.1700
Data Index: 5191960 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8435. Min Range: -7.8435
Max Act: 7.4060. Min Act: -0.1700
Data Index: 5521984 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8435. Min Range: -7.8435
Max Act: 7.3747. Min Act: -0.1700
Data Index: 6846786 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8435. Min Range: -7.8435
Max Act: 7.3747. Min Act: -0.1700
Data Index: 33812 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8435. Min Range: -7.8435
Max Act: 7.4060. Min Act: -0.1700
Data Index: 2785519 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8435. Min Range: -7.8435
Max Act: 7.3122. Min Act: -0.1700
Data Index: 2404599 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8435. Min Range: -7.8435
Max Act: 7.2810. Min Act: -0.1700
Data Index: 2211166 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8435. Min Range: -7.8435
Max Act: 7.2810. Min Act: -0.1700
Data Index: 474719 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8435. Min Range: -7.8435
Max Act: 7.2497. Min Act: -0.1700
Data Index: 6447891 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8435. Min Range: -7.8435
Max Act: 7.2185. Min Act: -0.1700
Data Index: 8105513 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8435. Min Range: -7.8435
Max Act: 7.1872. Min Act: -0.1700
Data Index: 622873 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8435. Min Range: -7.8435
Max Act: 7.1872. Min Act: -0.1700
Data Index: 5328557 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8435. Min Range: -7.8435
Max Act: 7.1560. Min Act: -0.1700
Data Index: 326128 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19