Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3289 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2798. Min Range: -8.2798
Max Act: 8.2798. Min Act: -0.1700
Data Index: 8400730 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2798. Min Range: -8.2798
Max Act: 8.2173. Min Act: -0.1700
Data Index: 5494178 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2798. Min Range: -8.2798
Max Act: 8.1548. Min Act: -0.1698
Data Index: 7306073 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2798. Min Range: -8.2798
Max Act: 8.1548. Min Act: -0.1700
Data Index: 3160591 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2798. Min Range: -8.2798
Max Act: 7.9673. Min Act: -0.1700
Data Index: 5494181 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2798. Min Range: -8.2798
Max Act: 7.9048. Min Act: -0.1700
Data Index: 159903 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2798. Min Range: -8.2798
Max Act: 7.9048. Min Act: -0.1700
Data Index: 3419851 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2798. Min Range: -8.2798
Max Act: 7.9048. Min Act: -0.1700
Data Index: 6851366 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2798. Min Range: -8.2798
Max Act: 7.8423. Min Act: -0.1700
Data Index: 2640670 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2798. Min Range: -8.2798
Max Act: 7.7798. Min Act: -0.1700
Data Index: 6059112 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2798. Min Range: -8.2798
Max Act: 7.7798. Min Act: -0.1700
Data Index: 5053859 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2798. Min Range: -8.2798
Max Act: 7.7798. Min Act: -0.1700
Data Index: 1877695 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2798. Min Range: -8.2798
Max Act: 7.7798. Min Act: -0.1700
Data Index: 4747089 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2798. Min Range: -8.2798
Max Act: 7.7173. Min Act: -0.1700
Data Index: 4317330 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2798. Min Range: -8.2798
Max Act: 7.7173. Min Act: -0.1700
Data Index: 4541281 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2798. Min Range: -8.2798
Max Act: 7.7173. Min Act: -0.1700
Data Index: 207510 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2798. Min Range: -8.2798
Max Act: 7.7173. Min Act: -0.1700
Data Index: 7142120 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2798. Min Range: -8.2798
Max Act: 7.7173. Min Act: -0.1700
Data Index: 5014845 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2798. Min Range: -8.2798
Max Act: 7.6548. Min Act: -0.1700
Data Index: 1833877 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2798. Min Range: -8.2798
Max Act: 7.6548. Min Act: -0.1700
Data Index: 3982844 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19