Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 835 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0556. Min Range: -8.0556
Max Act: 8.0556. Min Act: -0.1700
Data Index: 4816497 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0556. Min Range: -8.0556
Max Act: 7.9618. Min Act: -0.1700
Data Index: 3764280 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0556. Min Range: -8.0556
Max Act: 7.8993. Min Act: -0.1700
Data Index: 1999948 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0556. Min Range: -8.0556
Max Act: 7.8993. Min Act: -0.1700
Data Index: 4283807 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0556. Min Range: -8.0556
Max Act: 7.8368. Min Act: -0.1700
Data Index: 1086014 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0556. Min Range: -8.0556
Max Act: 7.5868. Min Act: -0.1700
Data Index: 2003623 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0556. Min Range: -8.0556
Max Act: 7.5556. Min Act: -0.1700
Data Index: 8609374 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0556. Min Range: -8.0556
Max Act: 7.4306. Min Act: -0.1700
Data Index: 3417702 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0556. Min Range: -8.0556
Max Act: 7.4306. Min Act: -0.1700
Data Index: 7419388 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0556. Min Range: -8.0556
Max Act: 7.2743. Min Act: -0.1700
Data Index: 4374434 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0556. Min Range: -8.0556
Max Act: 7.2431. Min Act: -0.1700
Data Index: 502349 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0556. Min Range: -8.0556
Max Act: 7.1493. Min Act: -0.1700
Data Index: 975522 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0556. Min Range: -8.0556
Max Act: 7.1493. Min Act: -0.1700
Data Index: 8609375 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0556. Min Range: -8.0556
Max Act: 7.0868. Min Act: -0.1700
Data Index: 7195374 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0556. Min Range: -8.0556
Max Act: 7.0556. Min Act: -0.1700
Data Index: 553523 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0556. Min Range: -8.0556
Max Act: 7.0556. Min Act: -0.1700
Data Index: 3622233 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0556. Min Range: -8.0556
Max Act: 7.0243. Min Act: -0.1700
Data Index: 8236264 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0556. Min Range: -8.0556
Max Act: 7.0243. Min Act: -0.1700
Data Index: 1086016 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0556. Min Range: -8.0556
Max Act: 7.0243. Min Act: -0.1700
Data Index: 2991880 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0556. Min Range: -8.0556
Max Act: 6.9931. Min Act: -0.1700
Data Index: 5077591 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19