Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1030 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1246. Min Range: -5.1246
Max Act: 5.1246. Min Act: -0.1700
Data Index: 5750966 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.9996. Min Act: -0.1700
Data Index: 4347164 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.9996. Min Act: -0.1700
Data Index: 4924318 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.9683. Min Act: -0.1700
Data Index: 5698130 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.9683. Min Act: -0.1700
Data Index: 7422603 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.9683. Min Act: -0.1700
Data Index: 8149365 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.9371. Min Act: -0.1700
Data Index: 7141880 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.9371. Min Act: -0.1700
Data Index: 279009 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.9683. Min Act: -0.1700
Data Index: 7215192 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.9371. Min Act: -0.1700
Data Index: 6879908 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.9058. Min Act: -0.1700
Data Index: 7852063 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.9058. Min Act: -0.1700
Data Index: 3133816 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.9058. Min Act: -0.1700
Data Index: 3160834 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.8433. Min Act: -0.1700
Data Index: 6103437 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.8746. Min Act: -0.1700
Data Index: 5636721 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.8746. Min Act: -0.1700
Data Index: 6245117 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.8746. Min Act: -0.1700
Data Index: 7248786 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.8433. Min Act: -0.1700
Data Index: 4471923 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.8433. Min Act: -0.1700
Data Index: 3818947 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1246. Min Range: -5.1246
Max Act: 4.8121. Min Act: -0.1700
Data Index: 6103444 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19