Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1394 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6589. Min Range: -8.6589
Max Act: 8.6589. Min Act: -0.1700
Data Index: 475493 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6589. Min Range: -8.6589
Max Act: 8.5964. Min Act: -0.1700
Data Index: 6817690 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6589. Min Range: -8.6589
Max Act: 8.5339. Min Act: -0.1700
Data Index: 726382 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6589. Min Range: -8.6589
Max Act: 8.4714. Min Act: -0.1700
Data Index: 4872349 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6589. Min Range: -8.6589
Max Act: 8.4714. Min Act: -0.1700
Data Index: 3875358 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6589. Min Range: -8.6589
Max Act: 8.4714. Min Act: -0.1700
Data Index: 2913873 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6589. Min Range: -8.6589
Max Act: 8.4714. Min Act: -0.1700
Data Index: 38212 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6589. Min Range: -8.6589
Max Act: 8.4089. Min Act: -0.1700
Data Index: 3392655 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6589. Min Range: -8.6589
Max Act: 8.4089. Min Act: -0.1700
Data Index: 3517497 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6589. Min Range: -8.6589
Max Act: 8.4089. Min Act: -0.1700
Data Index: 3950463 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6589. Min Range: -8.6589
Max Act: 8.4089. Min Act: -0.1700
Data Index: 6922678 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6589. Min Range: -8.6589
Max Act: 8.3464. Min Act: -0.1700
Data Index: 4044427 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6589. Min Range: -8.6589
Max Act: 8.2839. Min Act: -0.1700
Data Index: 660926 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6589. Min Range: -8.6589
Max Act: 8.3464. Min Act: -0.1700
Data Index: 2928679 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6589. Min Range: -8.6589
Max Act: 8.3464. Min Act: -0.1700
Data Index: 5875803 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6589. Min Range: -8.6589
Max Act: 8.3464. Min Act: -0.1700
Data Index: 7361076 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6589. Min Range: -8.6589
Max Act: 8.2839. Min Act: -0.1700
Data Index: 5875806 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6589. Min Range: -8.6589
Max Act: 8.2839. Min Act: -0.1700
Data Index: 4301737 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6589. Min Range: -8.6589
Max Act: 8.2839. Min Act: -0.1700
Data Index: 6419893 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6589. Min Range: -8.6589
Max Act: 8.2839. Min Act: -0.1700
Data Index: 6430485 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19