Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3361 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4197. Min Range: -8.4197
Max Act: 8.4197. Min Act: -0.1700
Data Index: 2285789 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4197. Min Range: -8.4197
Max Act: 8.2322. Min Act: -0.1700
Data Index: 2568867 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4197. Min Range: -8.4197
Max Act: 8.1697. Min Act: -0.1700
Data Index: 3910021 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4197. Min Range: -8.4197
Max Act: 8.0760. Min Act: -0.1700
Data Index: 7973186 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4197. Min Range: -8.4197
Max Act: 7.9822. Min Act: -0.1700
Data Index: 7063829 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4197. Min Range: -8.4197
Max Act: 7.9197. Min Act: -0.1700
Data Index: 2583325 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4197. Min Range: -8.4197
Max Act: 7.7947. Min Act: -0.1700
Data Index: 4121634 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4197. Min Range: -8.4197
Max Act: 7.7635. Min Act: -0.1700
Data Index: 726108 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4197. Min Range: -8.4197
Max Act: 7.7010. Min Act: -0.1700
Data Index: 1567565 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4197. Min Range: -8.4197
Max Act: 7.6697. Min Act: -0.1700
Data Index: 2826743 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4197. Min Range: -8.4197
Max Act: 7.6385. Min Act: -0.1700
Data Index: 7897320 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4197. Min Range: -8.4197
Max Act: 7.6697. Min Act: -0.1700
Data Index: 6432081 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4197. Min Range: -8.4197
Max Act: 7.6385. Min Act: -0.1700
Data Index: 3447946 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4197. Min Range: -8.4197
Max Act: 7.5760. Min Act: -0.1700
Data Index: 4030082 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4197. Min Range: -8.4197
Max Act: 7.6072. Min Act: -0.1700
Data Index: 2942914 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4197. Min Range: -8.4197
Max Act: 7.5760. Min Act: -0.1700
Data Index: 4322881 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4197. Min Range: -8.4197
Max Act: 7.5760. Min Act: -0.1700
Data Index: 3463697 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4197. Min Range: -8.4197
Max Act: 7.5135. Min Act: -0.1700
Data Index: 7634698 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4197. Min Range: -8.4197
Max Act: 7.5135. Min Act: -0.1700
Data Index: 7619464 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4197. Min Range: -8.4197
Max Act: 7.4822. Min Act: -0.1700
Data Index: 3622158 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19