Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1223 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5329. Min Range: -7.5329
Max Act: 7.5329. Min Act: -0.1700
Data Index: 1063797 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5329. Min Range: -7.5329
Max Act: 7.4079. Min Act: -0.1700
Data Index: 7620142 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5329. Min Range: -7.5329
Max Act: 7.2829. Min Act: -0.1700
Data Index: 1896891 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5329. Min Range: -7.5329
Max Act: 7.1266. Min Act: -0.1700
Data Index: 1323613 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5329. Min Range: -7.5329
Max Act: 7.0954. Min Act: -0.1700
Data Index: 3883837 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5329. Min Range: -7.5329
Max Act: 7.0641. Min Act: -0.1700
Data Index: 6187908 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5329. Min Range: -7.5329
Max Act: 7.0016. Min Act: -0.1700
Data Index: 4589246 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5329. Min Range: -7.5329
Max Act: 6.9079. Min Act: -0.1700
Data Index: 753089 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5329. Min Range: -7.5329
Max Act: 6.9704. Min Act: -0.1700
Data Index: 5139127 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5329. Min Range: -7.5329
Max Act: 6.9079. Min Act: -0.1700
Data Index: 1001546 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5329. Min Range: -7.5329
Max Act: 6.8454. Min Act: -0.1700
Data Index: 6110334 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5329. Min Range: -7.5329
Max Act: 6.8454. Min Act: -0.1700
Data Index: 1348933 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5329. Min Range: -7.5329
Max Act: 6.8141. Min Act: -0.1700
Data Index: 3222971 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5329. Min Range: -7.5329
Max Act: 6.7829. Min Act: -0.1700
Data Index: 982483 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5329. Min Range: -7.5329
Max Act: 6.8141. Min Act: -0.1700
Data Index: 4513856 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5329. Min Range: -7.5329
Max Act: 6.7516. Min Act: -0.1700
Data Index: 8784240 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5329. Min Range: -7.5329
Max Act: 6.7204. Min Act: -0.1700
Data Index: 972859 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5329. Min Range: -7.5329
Max Act: 6.7204. Min Act: -0.1700
Data Index: 766889 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5329. Min Range: -7.5329
Max Act: 6.6891. Min Act: -0.1700
Data Index: 6639506 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5329. Min Range: -7.5329
Max Act: 6.6579. Min Act: -0.1700
Data Index: 3948620 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19