Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3164 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6298. Min Range: -7.6298
Max Act: 7.6298. Min Act: -0.1700
Data Index: 4902809 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6298. Min Range: -7.6298
Max Act: 7.5673. Min Act: -0.1700
Data Index: 7743009 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6298. Min Range: -7.6298
Max Act: 7.5361. Min Act: -0.1700
Data Index: 1701435 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6298. Min Range: -7.6298
Max Act: 7.3798. Min Act: -0.1700
Data Index: 4690977 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6298. Min Range: -7.6298
Max Act: 7.3486. Min Act: -0.1700
Data Index: 873691 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6298. Min Range: -7.6298
Max Act: 7.2861. Min Act: -0.1700
Data Index: 3875161 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6298. Min Range: -7.6298
Max Act: 7.2236. Min Act: -0.1700
Data Index: 2923512 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6298. Min Range: -7.6298
Max Act: 7.1923. Min Act: -0.1700
Data Index: 873690 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6298. Min Range: -7.6298
Max Act: 7.1923. Min Act: -0.1700
Data Index: 7202249 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6298. Min Range: -7.6298
Max Act: 7.1298. Min Act: -0.1700
Data Index: 2262416 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6298. Min Range: -7.6298
Max Act: 7.1298. Min Act: -0.1700
Data Index: 3160609 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6298. Min Range: -7.6298
Max Act: 7.0986. Min Act: -0.1700
Data Index: 452518 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6298. Min Range: -7.6298
Max Act: 7.0673. Min Act: -0.1700
Data Index: 713671 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6298. Min Range: -7.6298
Max Act: 7.0673. Min Act: -0.1700
Data Index: 1311920 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6298. Min Range: -7.6298
Max Act: 6.9736. Min Act: -0.1700
Data Index: 1953049 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6298. Min Range: -7.6298
Max Act: 6.9736. Min Act: -0.1700
Data Index: 8481605 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6298. Min Range: -7.6298
Max Act: 6.9423. Min Act: -0.1700
Data Index: 8814062 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6298. Min Range: -7.6298
Max Act: 6.9423. Min Act: -0.1700
Data Index: 605032 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6298. Min Range: -7.6298
Max Act: 6.9423. Min Act: -0.1700
Data Index: 831708 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6298. Min Range: -7.6298
Max Act: 6.9423. Min Act: -0.1700
Data Index: 3317565 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19