Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5166 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2067. Min Range: -9.2067
Max Act: 9.2067. Min Act: -0.1700
Data Index: 7413360 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2067. Min Range: -9.2067
Max Act: 8.9567. Min Act: -0.1700
Data Index: 1386764 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2067. Min Range: -9.2067
Max Act: 8.8317. Min Act: -0.1700
Data Index: 2819349 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2067. Min Range: -9.2067
Max Act: 8.7067. Min Act: -0.1700
Data Index: 7413361 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2067. Min Range: -9.2067
Max Act: 8.6442. Min Act: -0.1700
Data Index: 6710395 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2067. Min Range: -9.2067
Max Act: 8.5817. Min Act: -0.1700
Data Index: 2409071 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2067. Min Range: -9.2067
Max Act: 8.5192. Min Act: -0.1700
Data Index: 6564903 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2067. Min Range: -9.2067
Max Act: 8.4567. Min Act: -0.1700
Data Index: 3504304 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2067. Min Range: -9.2067
Max Act: 8.4567. Min Act: -0.1700
Data Index: 6538278 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2067. Min Range: -9.2067
Max Act: 8.3317. Min Act: -0.1700
Data Index: 6710397 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2067. Min Range: -9.2067
Max Act: 8.3317. Min Act: -0.1700
Data Index: 8170760 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2067. Min Range: -9.2067
Max Act: 8.2692. Min Act: -0.1700
Data Index: 4104154 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2067. Min Range: -9.2067
Max Act: 8.2692. Min Act: -0.1700
Data Index: 1683262 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2067. Min Range: -9.2067
Max Act: 8.2692. Min Act: -0.1700
Data Index: 6886801 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2067. Min Range: -9.2067
Max Act: 8.2067. Min Act: -0.1700
Data Index: 3786325 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2067. Min Range: -9.2067
Max Act: 8.2067. Min Act: -0.1700
Data Index: 6085465 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2067. Min Range: -9.2067
Max Act: 8.2067. Min Act: -0.1700
Data Index: 4112003 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2067. Min Range: -9.2067
Max Act: 8.2067. Min Act: -0.1700
Data Index: 3292085 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2067. Min Range: -9.2067
Max Act: 8.2067. Min Act: -0.1700
Data Index: 850128 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2067. Min Range: -9.2067
Max Act: 8.2067. Min Act: -0.1700
Data Index: 4504570 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19