Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6324 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1022. Min Range: -7.1022
Max Act: 7.1022. Min Act: -0.1700
Data Index: 3926666 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1022. Min Range: -7.1022
Max Act: 6.9772. Min Act: -0.1700
Data Index: 3793937 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1022. Min Range: -7.1022
Max Act: 6.9460. Min Act: -0.1700
Data Index: 4942414 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1022. Min Range: -7.1022
Max Act: 6.8210. Min Act: -0.1700
Data Index: 1214208 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1022. Min Range: -7.1022
Max Act: 6.8210. Min Act: -0.1700
Data Index: 7328135 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1022. Min Range: -7.1022
Max Act: 6.7897. Min Act: -0.1700
Data Index: 2647021 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1022. Min Range: -7.1022
Max Act: 6.7897. Min Act: -0.1700
Data Index: 8714897 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1022. Min Range: -7.1022
Max Act: 6.7585. Min Act: -0.1700
Data Index: 7175678 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1022. Min Range: -7.1022
Max Act: 6.7272. Min Act: -0.1700
Data Index: 5591510 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1022. Min Range: -7.1022
Max Act: 6.6960. Min Act: -0.1700
Data Index: 4311652 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1022. Min Range: -7.1022
Max Act: 6.6960. Min Act: -0.1700
Data Index: 2004511 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1022. Min Range: -7.1022
Max Act: 6.6647. Min Act: -0.1700
Data Index: 1466556 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1022. Min Range: -7.1022
Max Act: 6.6647. Min Act: -0.1700
Data Index: 6336713 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1022. Min Range: -7.1022
Max Act: 6.6647. Min Act: -0.1700
Data Index: 5375356 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1022. Min Range: -7.1022
Max Act: 6.6335. Min Act: -0.1700
Data Index: 6478829 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1022. Min Range: -7.1022
Max Act: 6.6022. Min Act: -0.1700
Data Index: 7560631 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1022. Min Range: -7.1022
Max Act: 6.6022. Min Act: -0.1700
Data Index: 3947198 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1022. Min Range: -7.1022
Max Act: 6.6022. Min Act: -0.1700
Data Index: 1866903 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1022. Min Range: -7.1022
Max Act: 6.6022. Min Act: -0.1700
Data Index: 4736036 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1022. Min Range: -7.1022
Max Act: 6.5397. Min Act: -0.1700
Data Index: 1318279 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19