Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3572 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4679. Min Range: -8.4679
Max Act: 8.4679. Min Act: -0.1700
Data Index: 4031022 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4679. Min Range: -8.4679
Max Act: 8.2804. Min Act: -0.1700
Data Index: 8221075 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4679. Min Range: -8.4679
Max Act: 8.2804. Min Act: -0.1700
Data Index: 328477 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4679. Min Range: -8.4679
Max Act: 8.2179. Min Act: -0.1700
Data Index: 5464368 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4679. Min Range: -8.4679
Max Act: 8.0929. Min Act: -0.1700
Data Index: 7881818 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4679. Min Range: -8.4679
Max Act: 8.0929. Min Act: -0.1700
Data Index: 2613006 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4679. Min Range: -8.4679
Max Act: 7.9679. Min Act: -0.1700
Data Index: 7973780 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4679. Min Range: -8.4679
Max Act: 7.9679. Min Act: -0.1700
Data Index: 7030019 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4679. Min Range: -8.4679
Max Act: 7.9679. Min Act: -0.1700
Data Index: 2683355 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4679. Min Range: -8.4679
Max Act: 7.9054. Min Act: -0.1700
Data Index: 2499086 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4679. Min Range: -8.4679
Max Act: 7.9679. Min Act: -0.1700
Data Index: 4663491 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4679. Min Range: -8.4679
Max Act: 7.9054. Min Act: -0.1700
Data Index: 1052145 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4679. Min Range: -8.4679
Max Act: 7.9054. Min Act: -0.1700
Data Index: 2195806 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4679. Min Range: -8.4679
Max Act: 7.9054. Min Act: -0.1700
Data Index: 5727968 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4679. Min Range: -8.4679
Max Act: 7.9054. Min Act: -0.1700
Data Index: 7786173 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4679. Min Range: -8.4679
Max Act: 7.8429. Min Act: -0.1700
Data Index: 3074131 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4679. Min Range: -8.4679
Max Act: 7.8429. Min Act: -0.1700
Data Index: 8560624 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4679. Min Range: -8.4679
Max Act: 7.7804. Min Act: -0.1700
Data Index: 166609 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4679. Min Range: -8.4679
Max Act: 7.7804. Min Act: -0.1700
Data Index: 980944 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4679. Min Range: -8.4679
Max Act: 7.7179. Min Act: -0.1700
Data Index: 3551691 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19