Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3531 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5765. Min Range: -9.5765
Max Act: 9.5765. Min Act: -0.1700
Data Index: 8554420 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5765. Min Range: -9.5765
Max Act: 9.4515. Min Act: -0.1700
Data Index: 5370495 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5765. Min Range: -9.5765
Max Act: 9.3265. Min Act: -0.1700
Data Index: 8290213 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5765. Min Range: -9.5765
Max Act: 9.3890. Min Act: -0.1700
Data Index: 6985813 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5765. Min Range: -9.5765
Max Act: 9.3265. Min Act: -0.1700
Data Index: 6269704 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5765. Min Range: -9.5765
Max Act: 9.2015. Min Act: -0.1700
Data Index: 3948069 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5765. Min Range: -9.5765
Max Act: 9.2015. Min Act: -0.1700
Data Index: 3547841 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5765. Min Range: -9.5765
Max Act: 9.1390. Min Act: -0.1700
Data Index: 7639259 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5765. Min Range: -9.5765
Max Act: 9.0765. Min Act: -0.1700
Data Index: 8359058 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5765. Min Range: -9.5765
Max Act: 8.9515. Min Act: -0.1700
Data Index: 8194837 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5765. Min Range: -9.5765
Max Act: 8.9515. Min Act: -0.1700
Data Index: 1623773 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5765. Min Range: -9.5765
Max Act: 8.8890. Min Act: -0.1700
Data Index: 2032454 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5765. Min Range: -9.5765
Max Act: 8.8890. Min Act: -0.1700
Data Index: 1369715 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5765. Min Range: -9.5765
Max Act: 8.8265. Min Act: -0.1700
Data Index: 3120342 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5765. Min Range: -9.5765
Max Act: 8.8265. Min Act: -0.1700
Data Index: 7616802 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5765. Min Range: -9.5765
Max Act: 8.8265. Min Act: -0.1700
Data Index: 1240552 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5765. Min Range: -9.5765
Max Act: 8.8265. Min Act: -0.1700
Data Index: 2986656 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5765. Min Range: -9.5765
Max Act: 8.7640. Min Act: -0.1700
Data Index: 6944406 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5765. Min Range: -9.5765
Max Act: 8.7640. Min Act: -0.1700
Data Index: 1547641 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5765. Min Range: -9.5765
Max Act: 8.7640. Min Act: -0.1700
Data Index: 2071337 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19