Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1666 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4228. Min Range: -8.4228
Max Act: 8.4228. Min Act: -0.1700
Data Index: 7867363 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4228. Min Range: -8.4228
Max Act: 8.0478. Min Act: -0.1700
Data Index: 5608682 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4228. Min Range: -8.4228
Max Act: 7.9853. Min Act: -0.1700
Data Index: 7565261 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4228. Min Range: -8.4228
Max Act: 7.9853. Min Act: -0.1700
Data Index: 4936500 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4228. Min Range: -8.4228
Max Act: 7.9228. Min Act: -0.1700
Data Index: 869721 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4228. Min Range: -8.4228
Max Act: 7.9228. Min Act: -0.1700
Data Index: 8200383 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4228. Min Range: -8.4228
Max Act: 7.9228. Min Act: -0.1700
Data Index: 7172925 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4228. Min Range: -8.4228
Max Act: 7.8916. Min Act: -0.1700
Data Index: 6685695 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4228. Min Range: -8.4228
Max Act: 7.9228. Min Act: -0.1700
Data Index: 4464046 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4228. Min Range: -8.4228
Max Act: 7.8916. Min Act: -0.1700
Data Index: 272007 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4228. Min Range: -8.4228
Max Act: 7.8916. Min Act: -0.1700
Data Index: 7366353 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4228. Min Range: -8.4228
Max Act: 7.8603. Min Act: -0.1700
Data Index: 7565264 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4228. Min Range: -8.4228
Max Act: 7.8603. Min Act: -0.1700
Data Index: 5152088 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4228. Min Range: -8.4228
Max Act: 7.8291. Min Act: -0.1700
Data Index: 3359863 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4228. Min Range: -8.4228
Max Act: 7.8603. Min Act: -0.1700
Data Index: 5484697 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4228. Min Range: -8.4228
Max Act: 7.8291. Min Act: -0.1700
Data Index: 1726681 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4228. Min Range: -8.4228
Max Act: 7.7978. Min Act: -0.1700
Data Index: 4899029 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4228. Min Range: -8.4228
Max Act: 7.8291. Min Act: -0.1700
Data Index: 4888652 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4228. Min Range: -8.4228
Max Act: 7.7666. Min Act: -0.1700
Data Index: 3813779 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4228. Min Range: -8.4228
Max Act: 7.7666. Min Act: -0.1700
Data Index: 4066538 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19