Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2254 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.4926. Min Range: -12.4926
Max Act: 12.4926. Min Act: -0.1700
Data Index: 2138943 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.4926. Min Range: -12.4926
Max Act: 12.3051. Min Act: -0.1700
Data Index: 4900889 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.4926. Min Range: -12.4926
Max Act: 12.1801. Min Act: -0.1700
Data Index: 37005 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.4926. Min Range: -12.4926
Max Act: 11.6801. Min Act: -0.1700
Data Index: 7121466 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.4926. Min Range: -12.4926
Max Act: 11.4926. Min Act: -0.1700
Data Index: 2966522 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.4926. Min Range: -12.4926
Max Act: 11.4301. Min Act: -0.1700
Data Index: 2968663 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.4926. Min Range: -12.4926
Max Act: 11.1801. Min Act: -0.1700
Data Index: 1244399 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.4926. Min Range: -12.4926
Max Act: 11.1801. Min Act: -0.1700
Data Index: 4505966 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.4926. Min Range: -12.4926
Max Act: 11.1801. Min Act: -0.1700
Data Index: 7835200 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.4926. Min Range: -12.4926
Max Act: 11.1176. Min Act: -0.1700
Data Index: 6352530 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.4926. Min Range: -12.4926
Max Act: 11.1176. Min Act: -0.1700
Data Index: 8539851 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.4926. Min Range: -12.4926
Max Act: 11.0551. Min Act: -0.1700
Data Index: 2099297 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.4926. Min Range: -12.4926
Max Act: 10.9926. Min Act: -0.1700
Data Index: 7296706 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.4926. Min Range: -12.4926
Max Act: 10.9301. Min Act: -0.1700
Data Index: 443466 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.4926. Min Range: -12.4926
Max Act: 10.9301. Min Act: -0.1700
Data Index: 3072724 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.4926. Min Range: -12.4926
Max Act: 10.9301. Min Act: -0.1700
Data Index: 8372345 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.4926. Min Range: -12.4926
Max Act: 10.9301. Min Act: -0.1700
Data Index: 3626151 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.4926. Min Range: -12.4926
Max Act: 10.9301. Min Act: -0.1700
Data Index: 6955252 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.4926. Min Range: -12.4926
Max Act: 10.9301. Min Act: -0.1700
Data Index: 3426114 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.4926. Min Range: -12.4926
Max Act: 10.9301. Min Act: -0.1700
Data Index: 4159461 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19