Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5262 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7484. Min Range: -7.7484
Max Act: 7.7484. Min Act: -0.1700
Data Index: 2183335 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7484. Min Range: -7.7484
Max Act: 7.4359. Min Act: -0.1700
Data Index: 6214125 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7484. Min Range: -7.7484
Max Act: 7.4046. Min Act: -0.1700
Data Index: 52300 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7484. Min Range: -7.7484
Max Act: 7.3421. Min Act: -0.1700
Data Index: 5821309 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7484. Min Range: -7.7484
Max Act: 7.2796. Min Act: -0.1700
Data Index: 7949358 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7484. Min Range: -7.7484
Max Act: 7.2171. Min Act: -0.1700
Data Index: 3968922 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7484. Min Range: -7.7484
Max Act: 7.1859. Min Act: -0.1700
Data Index: 4715653 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7484. Min Range: -7.7484
Max Act: 7.1234. Min Act: -0.1700
Data Index: 4457060 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7484. Min Range: -7.7484
Max Act: 7.1234. Min Act: -0.1700
Data Index: 8301010 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7484. Min Range: -7.7484
Max Act: 7.1234. Min Act: -0.1700
Data Index: 4207927 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7484. Min Range: -7.7484
Max Act: 7.1234. Min Act: -0.1700
Data Index: 2870725 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7484. Min Range: -7.7484
Max Act: 7.1234. Min Act: -0.1700
Data Index: 1102964 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7484. Min Range: -7.7484
Max Act: 7.0921. Min Act: -0.1700
Data Index: 3065599 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7484. Min Range: -7.7484
Max Act: 7.0921. Min Act: -0.1700
Data Index: 3031992 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7484. Min Range: -7.7484
Max Act: 7.0609. Min Act: -0.1700
Data Index: 6647041 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7484. Min Range: -7.7484
Max Act: 6.9671. Min Act: -0.1700
Data Index: 3264099 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7484. Min Range: -7.7484
Max Act: 6.9671. Min Act: -0.1700
Data Index: 2521212 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7484. Min Range: -7.7484
Max Act: 6.9359. Min Act: -0.1700
Data Index: 5805623 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7484. Min Range: -7.7484
Max Act: 6.9671. Min Act: -0.1700
Data Index: 6346395 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7484. Min Range: -7.7484
Max Act: 6.9671. Min Act: -0.1700
Data Index: 8085827 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19