Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3504 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1254. Min Range: -8.1254
Max Act: 8.1254. Min Act: -0.1700
Data Index: 7681511 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1254. Min Range: -8.1254
Max Act: 8.0004. Min Act: -0.1700
Data Index: 4603079 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1254. Min Range: -8.1254
Max Act: 7.8129. Min Act: -0.1700
Data Index: 219801 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1254. Min Range: -8.1254
Max Act: 7.6254. Min Act: -0.1700
Data Index: 7905676 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1254. Min Range: -8.1254
Max Act: 7.5629. Min Act: -0.1700
Data Index: 2529979 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1254. Min Range: -8.1254
Max Act: 7.5317. Min Act: -0.1700
Data Index: 3842820 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1254. Min Range: -8.1254
Max Act: 7.4692. Min Act: -0.1700
Data Index: 4972151 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1254. Min Range: -8.1254
Max Act: 7.4692. Min Act: -0.1700
Data Index: 3881833 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1254. Min Range: -8.1254
Max Act: 7.4379. Min Act: -0.1700
Data Index: 7900662 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1254. Min Range: -8.1254
Max Act: 7.4379. Min Act: -0.1700
Data Index: 1246893 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1254. Min Range: -8.1254
Max Act: 7.4067. Min Act: -0.1700
Data Index: 5385469 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1254. Min Range: -8.1254
Max Act: 7.3754. Min Act: -0.1700
Data Index: 445734 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1254. Min Range: -8.1254
Max Act: 7.3442. Min Act: -0.1700
Data Index: 759768 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1254. Min Range: -8.1254
Max Act: 7.2817. Min Act: -0.1700
Data Index: 6638434 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1254. Min Range: -8.1254
Max Act: 7.2192. Min Act: -0.1700
Data Index: 1418868 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1254. Min Range: -8.1254
Max Act: 7.2192. Min Act: -0.1700
Data Index: 2675718 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1254. Min Range: -8.1254
Max Act: 7.1879. Min Act: -0.1700
Data Index: 5589804 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1254. Min Range: -8.1254
Max Act: 7.1567. Min Act: -0.1700
Data Index: 3889954 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1254. Min Range: -8.1254
Max Act: 7.1254. Min Act: -0.1700
Data Index: 445735 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1254. Min Range: -8.1254
Max Act: 7.0942. Min Act: -0.1700
Data Index: 3456972 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19