Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2052 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7985. Min Range: -4.7985
Max Act: 4.7985. Min Act: -0.1700
Data Index: 140899 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7985. Min Range: -4.7985
Max Act: 4.6110. Min Act: -0.1700
Data Index: 1870587 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7985. Min Range: -4.7985
Max Act: 4.5798. Min Act: -0.1700
Data Index: 6610816 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7985. Min Range: -4.7985
Max Act: 4.5798. Min Act: -0.1700
Data Index: 4536904 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7985. Min Range: -4.7985
Max Act: 4.5798. Min Act: -0.1700
Data Index: 24388 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7985. Min Range: -4.7985
Max Act: 4.4860. Min Act: -0.1700
Data Index: 5331911 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7985. Min Range: -4.7985
Max Act: 4.4235. Min Act: -0.1700
Data Index: 5759038 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7985. Min Range: -4.7985
Max Act: 4.3610. Min Act: -0.1700
Data Index: 5331912 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7985. Min Range: -4.7985
Max Act: 4.3610. Min Act: -0.1700
Data Index: 8466474 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7985. Min Range: -4.7985
Max Act: 4.3610. Min Act: -0.1700
Data Index: 903332 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7985. Min Range: -4.7985
Max Act: 4.3298. Min Act: -0.1700
Data Index: 7093205 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7985. Min Range: -4.7985
Max Act: 4.3298. Min Act: -0.1700
Data Index: 5331913 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7985. Min Range: -4.7985
Max Act: 4.2985. Min Act: -0.1700
Data Index: 1494854 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7985. Min Range: -4.7985
Max Act: 4.2672. Min Act: -0.1700
Data Index: 4756310 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7985. Min Range: -4.7985
Max Act: 4.2672. Min Act: -0.1700
Data Index: 6940688 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7985. Min Range: -4.7985
Max Act: 4.2360. Min Act: -0.1700
Data Index: 6152712 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7985. Min Range: -4.7985
Max Act: 4.2360. Min Act: -0.1700
Data Index: 7594824 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7985. Min Range: -4.7985
Max Act: 4.2360. Min Act: -0.1700
Data Index: 4156755 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7985. Min Range: -4.7985
Max Act: 4.2672. Min Act: -0.1700
Data Index: 7093204 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7985. Min Range: -4.7985
Max Act: 4.1735. Min Act: -0.1700
Data Index: 3912387 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19