Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1023 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.8897. Min Act: -0.1700
Data Index: 4934100 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.7943. Min Act: -0.1700
Data Index: 6041706 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.8103. Min Act: -0.1700
Data Index: 6214776 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.7943. Min Act: -0.1700
Data Index: 3622108 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.7784. Min Act: -0.1700
Data Index: 872887 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.7465. Min Act: -0.1700
Data Index: 7144854 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.7465. Min Act: -0.1700
Data Index: 3731620 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.7305. Min Act: -0.1700
Data Index: 1083009 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.7305. Min Act: -0.1700
Data Index: 7425099 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.7305. Min Act: -0.1700
Data Index: 31373 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.7305. Min Act: -0.1700
Data Index: 7912179 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.7145. Min Act: -0.1700
Data Index: 6473219 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.7145. Min Act: -0.1700
Data Index: 7453876 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.7145. Min Act: -0.1700
Data Index: 8632073 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.7145. Min Act: -0.1700
Data Index: 2544362 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.6985. Min Act: -0.1700
Data Index: 5262661 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.6985. Min Act: -0.1700
Data Index: 447357 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.6985. Min Act: -0.1700
Data Index: 8682307 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.6825. Min Act: -0.1700
Data Index: 1952973 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.6825. Min Act: -0.1700
Data Index: 3032427 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19