Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5014 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5102. Min Range: -7.5102
Max Act: 7.5102. Min Act: -0.1700
Data Index: 6345421 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5102. Min Range: -7.5102
Max Act: 7.4477. Min Act: -0.1700
Data Index: 8020596 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5102. Min Range: -7.5102
Max Act: 7.4165. Min Act: -0.1700
Data Index: 3700551 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5102. Min Range: -7.5102
Max Act: 7.2602. Min Act: -0.1700
Data Index: 7875937 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5102. Min Range: -7.5102
Max Act: 7.2602. Min Act: -0.1700
Data Index: 3856780 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5102. Min Range: -7.5102
Max Act: 7.2290. Min Act: -0.1700
Data Index: 2619056 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5102. Min Range: -7.5102
Max Act: 7.2290. Min Act: -0.1700
Data Index: 5832024 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5102. Min Range: -7.5102
Max Act: 7.1665. Min Act: -0.1700
Data Index: 4314179 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5102. Min Range: -7.5102
Max Act: 7.1352. Min Act: -0.1700
Data Index: 7591861 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5102. Min Range: -7.5102
Max Act: 7.1352. Min Act: -0.1700
Data Index: 6455485 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5102. Min Range: -7.5102
Max Act: 7.0727. Min Act: -0.1700
Data Index: 1442003 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5102. Min Range: -7.5102
Max Act: 7.0415. Min Act: -0.1700
Data Index: 6473506 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5102. Min Range: -7.5102
Max Act: 7.0102. Min Act: -0.1700
Data Index: 2917490 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5102. Min Range: -7.5102
Max Act: 7.0102. Min Act: -0.1700
Data Index: 8331127 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5102. Min Range: -7.5102
Max Act: 6.9477. Min Act: -0.1700
Data Index: 528854 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5102. Min Range: -7.5102
Max Act: 6.9790. Min Act: -0.1700
Data Index: 191414 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5102. Min Range: -7.5102
Max Act: 7.0102. Min Act: -0.1700
Data Index: 710909 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5102. Min Range: -7.5102
Max Act: 6.9477. Min Act: -0.1700
Data Index: 5768178 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5102. Min Range: -7.5102
Max Act: 6.9477. Min Act: -0.1700
Data Index: 918901 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5102. Min Range: -7.5102
Max Act: 6.9477. Min Act: -0.1700
Data Index: 6040417 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19