Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2705 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1627. Min Range: -10.1627
Max Act: 10.1002. Min Act: -0.1700
Data Index: 8257192 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1627. Min Range: -10.1627
Max Act: 10.1627. Min Act: -0.1700
Data Index: 8257213 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1627. Min Range: -10.1627
Max Act: 9.9127. Min Act: -0.1700
Data Index: 8257214 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1627. Min Range: -10.1627
Max Act: 9.6627. Min Act: -0.1700
Data Index: 8686182 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1627. Min Range: -10.1627
Max Act: 9.6627. Min Act: -0.1700
Data Index: 8686169 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1627. Min Range: -10.1627
Max Act: 9.6002. Min Act: -0.1700
Data Index: 8653805 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1627. Min Range: -10.1627
Max Act: 9.6002. Min Act: -0.1700
Data Index: 5056228 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1627. Min Range: -10.1627
Max Act: 9.6002. Min Act: -0.1700
Data Index: 5056212 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1627. Min Range: -10.1627
Max Act: 9.5377. Min Act: -0.1700
Data Index: 5657926 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1627. Min Range: -10.1627
Max Act: 9.5377. Min Act: -0.1700
Data Index: 8367964 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1627. Min Range: -10.1627
Max Act: 9.5377. Min Act: -0.1700
Data Index: 3560450 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1627. Min Range: -10.1627
Max Act: 9.4752. Min Act: -0.1700
Data Index: 8070615 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1627. Min Range: -10.1627
Max Act: 9.4752. Min Act: -0.1700
Data Index: 311750 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1627. Min Range: -10.1627
Max Act: 9.4752. Min Act: -0.1700
Data Index: 5469011 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1627. Min Range: -10.1627
Max Act: 9.4752. Min Act: -0.1700
Data Index: 2746199 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1627. Min Range: -10.1627
Max Act: 9.4127. Min Act: -0.1700
Data Index: 8257193 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1627. Min Range: -10.1627
Max Act: 9.4127. Min Act: -0.1700
Data Index: 3378103 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1627. Min Range: -10.1627
Max Act: 9.4127. Min Act: -0.1700
Data Index: 8070639 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1627. Min Range: -10.1627
Max Act: 9.4127. Min Act: -0.1700
Data Index: 6648677 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1627. Min Range: -10.1627
Max Act: 9.4127. Min Act: -0.1700
Data Index: 2746196 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19