Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 180 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5302. Min Range: -10.5302
Max Act: 10.5302. Min Act: -0.1700
Data Index: 8748592 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5302. Min Range: -10.5302
Max Act: 9.8427. Min Act: -0.1700
Data Index: 898710 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5302. Min Range: -10.5302
Max Act: 9.7177. Min Act: -0.1700
Data Index: 1218093 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5302. Min Range: -10.5302
Max Act: 9.7802. Min Act: -0.1700
Data Index: 187697 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5302. Min Range: -10.5302
Max Act: 9.7802. Min Act: -0.1700
Data Index: 6000254 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5302. Min Range: -10.5302
Max Act: 9.5927. Min Act: -0.1700
Data Index: 5001299 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5302. Min Range: -10.5302
Max Act: 9.5302. Min Act: -0.1700
Data Index: 2387899 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5302. Min Range: -10.5302
Max Act: 9.4677. Min Act: -0.1700
Data Index: 6566569 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5302. Min Range: -10.5302
Max Act: 9.4677. Min Act: -0.1700
Data Index: 1218094 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5302. Min Range: -10.5302
Max Act: 9.4677. Min Act: -0.1700
Data Index: 8044750 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5302. Min Range: -10.5302
Max Act: 9.4052. Min Act: -0.1700
Data Index: 2245855 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5302. Min Range: -10.5302
Max Act: 9.4677. Min Act: -0.1700
Data Index: 3680078 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5302. Min Range: -10.5302
Max Act: 9.4052. Min Act: -0.1700
Data Index: 1106887 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5302. Min Range: -10.5302
Max Act: 9.4052. Min Act: -0.1700
Data Index: 8475547 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5302. Min Range: -10.5302
Max Act: 9.4052. Min Act: -0.1700
Data Index: 671511 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5302. Min Range: -10.5302
Max Act: 9.3427. Min Act: -0.1700
Data Index: 8421205 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5302. Min Range: -10.5302
Max Act: 9.3427. Min Act: -0.1700
Data Index: 7909385 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5302. Min Range: -10.5302
Max Act: 9.3427. Min Act: -0.1700
Data Index: 8282331 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5302. Min Range: -10.5302
Max Act: 9.3427. Min Act: -0.1700
Data Index: 1178274 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5302. Min Range: -10.5302
Max Act: 9.3427. Min Act: -0.1700
Data Index: 6243873 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19