Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2844 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0391. Min Range: -9.0391
Max Act: 9.0391. Min Act: -0.1700
Data Index: 3684060 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0391. Min Range: -9.0391
Max Act: 8.6641. Min Act: -0.1700
Data Index: 4181712 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0391. Min Range: -9.0391
Max Act: 8.5391. Min Act: -0.1700
Data Index: 267278 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0391. Min Range: -9.0391
Max Act: 8.5391. Min Act: -0.1700
Data Index: 5072243 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0391. Min Range: -9.0391
Max Act: 8.4766. Min Act: -0.1700
Data Index: 6419998 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0391. Min Range: -9.0391
Max Act: 8.4766. Min Act: -0.1700
Data Index: 809148 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0391. Min Range: -9.0391
Max Act: 8.4766. Min Act: -0.1700
Data Index: 7685076 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0391. Min Range: -9.0391
Max Act: 8.4141. Min Act: -0.1700
Data Index: 2334652 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0391. Min Range: -9.0391
Max Act: 8.3516. Min Act: -0.1700
Data Index: 3901143 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0391. Min Range: -9.0391
Max Act: 8.3516. Min Act: -0.1700
Data Index: 2777588 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0391. Min Range: -9.0391
Max Act: 8.2266. Min Act: -0.1700
Data Index: 5902022 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0391. Min Range: -9.0391
Max Act: 8.2266. Min Act: -0.1700
Data Index: 8671443 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0391. Min Range: -9.0391
Max Act: 8.2266. Min Act: -0.1700
Data Index: 6574737 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0391. Min Range: -9.0391
Max Act: 8.2266. Min Act: -0.1700
Data Index: 2809923 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0391. Min Range: -9.0391
Max Act: 8.2266. Min Act: -0.1700
Data Index: 2626023 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0391. Min Range: -9.0391
Max Act: 8.2266. Min Act: -0.1700
Data Index: 2309331 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0391. Min Range: -9.0391
Max Act: 8.1641. Min Act: -0.1700
Data Index: 121352 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0391. Min Range: -9.0391
Max Act: 8.1641. Min Act: -0.1700
Data Index: 437835 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0391. Min Range: -9.0391
Max Act: 8.1641. Min Act: -0.1700
Data Index: 1363765 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0391. Min Range: -9.0391
Max Act: 8.1641. Min Act: -0.1700
Data Index: 326769 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19