Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3174 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3551. Min Range: -4.3551
Max Act: 4.3551. Min Act: -0.1700
Data Index: 886012 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3551. Min Range: -4.3551
Max Act: 4.3239. Min Act: -0.1700
Data Index: 1810745 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3551. Min Range: -4.3551
Max Act: 4.1051. Min Act: -0.1700
Data Index: 6553798 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3551. Min Range: -4.3551
Max Act: 4.1363. Min Act: -0.1700
Data Index: 7970962 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3551. Min Range: -4.3551
Max Act: 4.1051. Min Act: -0.1700
Data Index: 1581270 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3551. Min Range: -4.3551
Max Act: 4.0738. Min Act: -0.1700
Data Index: 1034219 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3551. Min Range: -4.3551
Max Act: 4.0426. Min Act: -0.1700
Data Index: 5429464 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3551. Min Range: -4.3551
Max Act: 3.9488. Min Act: -0.1700
Data Index: 243052 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3551. Min Range: -4.3551
Max Act: 3.9175. Min Act: -0.1700
Data Index: 7801766 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3551. Min Range: -4.3551
Max Act: 3.9175. Min Act: -0.1700
Data Index: 6913413 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3551. Min Range: -4.3551
Max Act: 3.9175. Min Act: -0.1700
Data Index: 5563481 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3551. Min Range: -4.3551
Max Act: 3.9175. Min Act: -0.1700
Data Index: 629645 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3551. Min Range: -4.3551
Max Act: 3.8863. Min Act: -0.1700
Data Index: 4915677 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3551. Min Range: -4.3551
Max Act: 3.8550. Min Act: -0.1700
Data Index: 1429436 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3551. Min Range: -4.3551
Max Act: 3.8706. Min Act: -0.1700
Data Index: 5326553 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3551. Min Range: -4.3551
Max Act: 3.8237. Min Act: -0.1700
Data Index: 5090263 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3551. Min Range: -4.3551
Max Act: 3.8081. Min Act: -0.1700
Data Index: 941981 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3551. Min Range: -4.3551
Max Act: 3.7925. Min Act: -0.1700
Data Index: 4698294 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3551. Min Range: -4.3551
Max Act: 3.7768. Min Act: -0.1700
Data Index: 4634992 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3551. Min Range: -4.3551
Max Act: 3.7925. Min Act: -0.1700
Data Index: 8449021 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19