Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3847 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4516. Min Range: -7.4516
Max Act: 7.4516. Min Act: -0.1700
Data Index: 8200739 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4516. Min Range: -7.4516
Max Act: 7.2329. Min Act: -0.1700
Data Index: 5738258 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4516. Min Range: -7.4516
Max Act: 7.1704. Min Act: -0.1700
Data Index: 1441645 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4516. Min Range: -7.4516
Max Act: 7.1391. Min Act: -0.1700
Data Index: 8551617 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4516. Min Range: -7.4516
Max Act: 7.0766. Min Act: -0.1700
Data Index: 6710791 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4516. Min Range: -7.4516
Max Act: 7.1391. Min Act: -0.1700
Data Index: 3542353 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4516. Min Range: -7.4516
Max Act: 7.0766. Min Act: -0.1700
Data Index: 5847160 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4516. Min Range: -7.4516
Max Act: 6.9829. Min Act: -0.1700
Data Index: 5505287 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4516. Min Range: -7.4516
Max Act: 6.9516. Min Act: -0.1698
Data Index: 5679950 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4516. Min Range: -7.4516
Max Act: 6.9516. Min Act: -0.1700
Data Index: 5122875 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4516. Min Range: -7.4516
Max Act: 6.9204. Min Act: -0.1700
Data Index: 1601939 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4516. Min Range: -7.4516
Max Act: 6.8891. Min Act: -0.1700
Data Index: 5272022 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4516. Min Range: -7.4516
Max Act: 6.9204. Min Act: -0.1700
Data Index: 7369779 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4516. Min Range: -7.4516
Max Act: 6.8891. Min Act: -0.1700
Data Index: 8551616 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4516. Min Range: -7.4516
Max Act: 6.9204. Min Act: -0.1700
Data Index: 4274429 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4516. Min Range: -7.4516
Max Act: 6.8891. Min Act: -0.1700
Data Index: 4820681 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4516. Min Range: -7.4516
Max Act: 6.8579. Min Act: -0.1700
Data Index: 5644215 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4516. Min Range: -7.4516
Max Act: 6.8579. Min Act: -0.1700
Data Index: 8257018 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4516. Min Range: -7.4516
Max Act: 6.8579. Min Act: -0.1700
Data Index: 7264247 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4516. Min Range: -7.4516
Max Act: 6.8579. Min Act: -0.1700
Data Index: 5617210 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19