Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4583 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1045. Min Range: -8.1045
Max Act: 8.1045. Min Act: -0.1700
Data Index: 3224341 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1045. Min Range: -8.1045
Max Act: 7.4170. Min Act: -0.1700
Data Index: 2458097 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1045. Min Range: -8.1045
Max Act: 7.3233. Min Act: -0.1700
Data Index: 7886812 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1045. Min Range: -8.1045
Max Act: 7.2920. Min Act: -0.1700
Data Index: 6778587 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1045. Min Range: -8.1045
Max Act: 7.2920. Min Act: -0.1700
Data Index: 6727892 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1045. Min Range: -8.1045
Max Act: 7.2295. Min Act: -0.1700
Data Index: 3178051 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1045. Min Range: -8.1045
Max Act: 7.1983. Min Act: -0.1700
Data Index: 2334837 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1045. Min Range: -8.1045
Max Act: 7.2295. Min Act: -0.1700
Data Index: 3030231 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1045. Min Range: -8.1045
Max Act: 7.2295. Min Act: -0.1700
Data Index: 2887493 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1045. Min Range: -8.1045
Max Act: 7.1358. Min Act: -0.1700
Data Index: 1179244 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1045. Min Range: -8.1045
Max Act: 7.1358. Min Act: -0.1700
Data Index: 8118803 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1045. Min Range: -8.1045
Max Act: 7.1358. Min Act: -0.1700
Data Index: 5853735 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1045. Min Range: -8.1045
Max Act: 7.1045. Min Act: -0.1700
Data Index: 7635750 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1045. Min Range: -8.1045
Max Act: 7.1045. Min Act: -0.1700
Data Index: 1879917 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1045. Min Range: -8.1045
Max Act: 7.0420. Min Act: -0.1700
Data Index: 1781423 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1045. Min Range: -8.1045
Max Act: 7.0420. Min Act: -0.1700
Data Index: 8015273 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1045. Min Range: -8.1045
Max Act: 7.0420. Min Act: -0.1700
Data Index: 7015179 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1045. Min Range: -8.1045
Max Act: 6.9795. Min Act: -0.1700
Data Index: 1600061 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1045. Min Range: -8.1045
Max Act: 6.9795. Min Act: -0.1700
Data Index: 2966246 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1045. Min Range: -8.1045
Max Act: 6.9483. Min Act: -0.1700
Data Index: 4505955 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19