Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3106 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1702. Min Range: -8.1702
Max Act: 8.1702. Min Act: -0.1700
Data Index: 4528838 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1702. Min Range: -8.1702
Max Act: 8.0452. Min Act: -0.1700
Data Index: 2648409 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1702. Min Range: -8.1702
Max Act: 7.9827. Min Act: -0.1700
Data Index: 4300493 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1702. Min Range: -8.1702
Max Act: 7.9827. Min Act: -0.1700
Data Index: 842740 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1702. Min Range: -8.1702
Max Act: 7.9202. Min Act: -0.1700
Data Index: 1056543 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1702. Min Range: -8.1702
Max Act: 7.9202. Min Act: -0.1700
Data Index: 7858936 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1702. Min Range: -8.1702
Max Act: 7.8577. Min Act: -0.1700
Data Index: 3047954 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1702. Min Range: -8.1702
Max Act: 7.8577. Min Act: -0.1700
Data Index: 8241673 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1702. Min Range: -8.1702
Max Act: 7.8577. Min Act: -0.1700
Data Index: 4492510 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1702. Min Range: -8.1702
Max Act: 7.7952. Min Act: -0.1700
Data Index: 7979531 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1702. Min Range: -8.1702
Max Act: 7.7952. Min Act: -0.1700
Data Index: 6485925 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1702. Min Range: -8.1702
Max Act: 7.7327. Min Act: -0.1700
Data Index: 8628125 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1702. Min Range: -8.1702
Max Act: 7.6702. Min Act: -0.1700
Data Index: 2071920 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1702. Min Range: -8.1702
Max Act: 7.6702. Min Act: -0.1700
Data Index: 6040164 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1702. Min Range: -8.1702
Max Act: 7.7327. Min Act: -0.1700
Data Index: 5475784 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1702. Min Range: -8.1702
Max Act: 7.7952. Min Act: -0.1700
Data Index: 8005350 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1702. Min Range: -8.1702
Max Act: 7.7327. Min Act: -0.1700
Data Index: 4763784 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1702. Min Range: -8.1702
Max Act: 7.6702. Min Act: -0.1700
Data Index: 4454011 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1702. Min Range: -8.1702
Max Act: 7.6702. Min Act: -0.1700
Data Index: 7187939 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1702. Min Range: -8.1702
Max Act: 7.6702. Min Act: -0.1700
Data Index: 1011709 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19