Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 401 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8990. Min Range: -2.8990
Max Act: 2.8990. Min Act: -0.1700
Data Index: 7062030 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8990. Min Range: -2.8990
Max Act: 2.8673. Min Act: -0.1700
Data Index: 3612032 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8990. Min Range: -2.8990
Max Act: 2.8196. Min Act: -0.1700
Data Index: 1654252 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8990. Min Range: -2.8990
Max Act: 2.7877. Min Act: -0.1700
Data Index: 3986302 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8990. Min Range: -2.8990
Max Act: 2.7718. Min Act: -0.1700
Data Index: 6162095 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8990. Min Range: -2.8990
Max Act: 2.7877. Min Act: -0.1700
Data Index: 6405923 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8990. Min Range: -2.8990
Max Act: 2.7239. Min Act: -0.1700
Data Index: 991715 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8990. Min Range: -2.8990
Max Act: 2.7558. Min Act: -0.1700
Data Index: 7306723 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8990. Min Range: -2.8990
Max Act: 2.7718. Min Act: -0.1700
Data Index: 4563803 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8990. Min Range: -2.8990
Max Act: 2.7239. Min Act: -0.1700
Data Index: 1127992 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8990. Min Range: -2.8990
Max Act: 2.7399. Min Act: -0.1700
Data Index: 5527045 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8990. Min Range: -2.8990
Max Act: 2.7399. Min Act: -0.1700
Data Index: 4646810 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8990. Min Range: -2.8990
Max Act: 2.7399. Min Act: -0.1700
Data Index: 1341902 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8990. Min Range: -2.8990
Max Act: 2.7239. Min Act: -0.1700
Data Index: 3320241 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8990. Min Range: -2.8990
Max Act: 2.7079. Min Act: -0.1700
Data Index: 7637834 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8990. Min Range: -2.8990
Max Act: 2.7239. Min Act: -0.1700
Data Index: 5527042 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8990. Min Range: -2.8990
Max Act: 2.7079. Min Act: -0.1700
Data Index: 3223673 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8990. Min Range: -2.8990
Max Act: 2.6919. Min Act: -0.1700
Data Index: 1794080 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8990. Min Range: -2.8990
Max Act: 2.6599. Min Act: -0.1700
Data Index: 2736627 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8990. Min Range: -2.8990
Max Act: 2.6919. Min Act: -0.1700
Data Index: 3134186 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19