Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4532 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1227. Min Range: -8.1227
Max Act: 8.1227. Min Act: -0.1700
Data Index: 7265234 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1227. Min Range: -8.1227
Max Act: 8.1227. Min Act: -0.1700
Data Index: 2564928 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1227. Min Range: -8.1227
Max Act: 8.1227. Min Act: -0.1700
Data Index: 6711364 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1227. Min Range: -8.1227
Max Act: 8.0602. Min Act: -0.1700
Data Index: 5084561 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1227. Min Range: -8.1227
Max Act: 7.9977. Min Act: -0.1700
Data Index: 5084563 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1227. Min Range: -8.1227
Max Act: 8.0602. Min Act: -0.1700
Data Index: 7866542 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1227. Min Range: -8.1227
Max Act: 7.9352. Min Act: -0.1700
Data Index: 4537269 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1227. Min Range: -8.1227
Max Act: 7.8727. Min Act: -0.1700
Data Index: 1136262 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1227. Min Range: -8.1227
Max Act: 7.8727. Min Act: -0.1700
Data Index: 6783975 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1227. Min Range: -8.1227
Max Act: 7.8102. Min Act: -0.1700
Data Index: 7879093 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1227. Min Range: -8.1227
Max Act: 7.7477. Min Act: -0.1700
Data Index: 1039033 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1227. Min Range: -8.1227
Max Act: 7.7477. Min Act: -0.1700
Data Index: 8691921 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1227. Min Range: -8.1227
Max Act: 7.7477. Min Act: -0.1700
Data Index: 5797606 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1227. Min Range: -8.1227
Max Act: 7.7477. Min Act: -0.1700
Data Index: 2278638 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1227. Min Range: -8.1227
Max Act: 7.7477. Min Act: -0.1700
Data Index: 8371131 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1227. Min Range: -8.1227
Max Act: 7.6852. Min Act: -0.1700
Data Index: 4484425 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1227. Min Range: -8.1227
Max Act: 7.6852. Min Act: -0.1700
Data Index: 8780302 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1227. Min Range: -8.1227
Max Act: 7.6227. Min Act: -0.1700
Data Index: 2270839 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1227. Min Range: -8.1227
Max Act: 7.6227. Min Act: -0.1700
Data Index: 2849790 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1227. Min Range: -8.1227
Max Act: 7.6227. Min Act: -0.1700
Data Index: 625039 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19