Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2490 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4765. Min Range: -4.4765
Max Act: 4.4765. Min Act: -0.1700
Data Index: 1373299 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4765. Min Range: -4.4765
Max Act: 4.4453. Min Act: -0.1700
Data Index: 543564 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4765. Min Range: -4.4765
Max Act: 4.4140. Min Act: -0.1700
Data Index: 5727354 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4765. Min Range: -4.4765
Max Act: 4.4140. Min Act: -0.1700
Data Index: 1862141 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4765. Min Range: -4.4765
Max Act: 4.3515. Min Act: -0.1700
Data Index: 6792918 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4765. Min Range: -4.4765
Max Act: 4.3828. Min Act: -0.1700
Data Index: 5519553 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4765. Min Range: -4.4765
Max Act: 4.3203. Min Act: -0.1700
Data Index: 2110928 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4765. Min Range: -4.4765
Max Act: 4.3515. Min Act: -0.1700
Data Index: 3500796 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4765. Min Range: -4.4765
Max Act: 4.3515. Min Act: -0.1700
Data Index: 8506741 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4765. Min Range: -4.4765
Max Act: 4.3515. Min Act: -0.1700
Data Index: 6839403 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4765. Min Range: -4.4765
Max Act: 4.3515. Min Act: -0.1700
Data Index: 6557017 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4765. Min Range: -4.4765
Max Act: 4.3515. Min Act: -0.1700
Data Index: 7260931 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4765. Min Range: -4.4765
Max Act: 4.3203. Min Act: -0.1700
Data Index: 5616722 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4765. Min Range: -4.4765
Max Act: 4.3203. Min Act: -0.1700
Data Index: 8608557 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4765. Min Range: -4.4765
Max Act: 4.3203. Min Act: -0.1700
Data Index: 4543805 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4765. Min Range: -4.4765
Max Act: 4.3203. Min Act: -0.1700
Data Index: 213993 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4765. Min Range: -4.4765
Max Act: 4.2890. Min Act: -0.1700
Data Index: 4443330 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4765. Min Range: -4.4765
Max Act: 4.2890. Min Act: -0.1700
Data Index: 2922232 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4765. Min Range: -4.4765
Max Act: 4.2890. Min Act: -0.1700
Data Index: 197051 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4765. Min Range: -4.4765
Max Act: 4.2890. Min Act: -0.1700
Data Index: 1183663 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19