Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3469 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6931. Min Range: -7.6931
Max Act: 7.6931. Min Act: -0.1700
Data Index: 7485933 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6931. Min Range: -7.6931
Max Act: 7.3806. Min Act: -0.1700
Data Index: 6855012 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6931. Min Range: -7.6931
Max Act: 7.2243. Min Act: -0.1700
Data Index: 8600190 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6931. Min Range: -7.6931
Max Act: 7.1931. Min Act: -0.1700
Data Index: 1077533 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6931. Min Range: -7.6931
Max Act: 7.1931. Min Act: -0.1700
Data Index: 8546732 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6931. Min Range: -7.6931
Max Act: 7.1931. Min Act: -0.1700
Data Index: 837904 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6931. Min Range: -7.6931
Max Act: 7.0056. Min Act: -0.1700
Data Index: 2045301 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6931. Min Range: -7.6931
Max Act: 6.9743. Min Act: -0.1700
Data Index: 6319392 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6931. Min Range: -7.6931
Max Act: 6.8806. Min Act: -0.1700
Data Index: 4901324 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6931. Min Range: -7.6931
Max Act: 6.8493. Min Act: -0.1700
Data Index: 6826578 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6931. Min Range: -7.6931
Max Act: 6.8493. Min Act: -0.1700
Data Index: 7003381 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6931. Min Range: -7.6931
Max Act: 6.8181. Min Act: -0.1700
Data Index: 1427100 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6931. Min Range: -7.6931
Max Act: 6.7868. Min Act: -0.1700
Data Index: 7012504 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6931. Min Range: -7.6931
Max Act: 6.7868. Min Act: -0.1700
Data Index: 816901 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6931. Min Range: -7.6931
Max Act: 6.7556. Min Act: -0.1700
Data Index: 519400 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6931. Min Range: -7.6931
Max Act: 6.7243. Min Act: -0.1700
Data Index: 5885405 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6931. Min Range: -7.6931
Max Act: 6.7243. Min Act: -0.1700
Data Index: 5126184 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6931. Min Range: -7.6931
Max Act: 6.6931. Min Act: -0.1700
Data Index: 6492758 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6931. Min Range: -7.6931
Max Act: 6.6618. Min Act: -0.1700
Data Index: 8501428 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6931. Min Range: -7.6931
Max Act: 6.6931. Min Act: -0.1700
Data Index: 6934566 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19