Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3529 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.7301. Min Range: -11.7301
Max Act: 11.7301. Min Act: -0.1700
Data Index: 1129077 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.7301. Min Range: -11.7301
Max Act: 10.4176. Min Act: -0.1700
Data Index: 7662764 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.7301. Min Range: -11.7301
Max Act: 10.2926. Min Act: -0.1700
Data Index: 2648591 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.7301. Min Range: -11.7301
Max Act: 10.2926. Min Act: -0.1700
Data Index: 2225169 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.7301. Min Range: -11.7301
Max Act: 10.1676. Min Act: -0.1700
Data Index: 5841172 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.7301. Min Range: -11.7301
Max Act: 10.1051. Min Act: -0.1700
Data Index: 2993235 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.7301. Min Range: -11.7301
Max Act: 10.1051. Min Act: -0.1700
Data Index: 8309784 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.7301. Min Range: -11.7301
Max Act: 10.0426. Min Act: -0.1700
Data Index: 130935 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.7301. Min Range: -11.7301
Max Act: 9.9801. Min Act: -0.1700
Data Index: 3128255 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.7301. Min Range: -11.7301
Max Act: 9.9801. Min Act: -0.1700
Data Index: 1982170 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.7301. Min Range: -11.7301
Max Act: 9.9801. Min Act: -0.1700
Data Index: 613954 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.7301. Min Range: -11.7301
Max Act: 9.9176. Min Act: -0.1700
Data Index: 7522132 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.7301. Min Range: -11.7301
Max Act: 9.9176. Min Act: -0.1700
Data Index: 3700182 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.7301. Min Range: -11.7301
Max Act: 9.9176. Min Act: -0.1700
Data Index: 4718817 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.7301. Min Range: -11.7301
Max Act: 9.9176. Min Act: -0.1700
Data Index: 7073572 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.7301. Min Range: -11.7301
Max Act: 9.8551. Min Act: -0.1700
Data Index: 3461017 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.7301. Min Range: -11.7301
Max Act: 9.8551. Min Act: -0.1700
Data Index: 2054060 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.7301. Min Range: -11.7301
Max Act: 9.8551. Min Act: -0.1700
Data Index: 1976980 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.7301. Min Range: -11.7301
Max Act: 9.8551. Min Act: -0.1700
Data Index: 4333272 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.7301. Min Range: -11.7301
Max Act: 9.7926. Min Act: -0.1700
Data Index: 1566932 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19