Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3909 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9611. Min Range: -7.9611
Max Act: 7.9611. Min Act: -0.1700
Data Index: 4116221 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9611. Min Range: -7.9611
Max Act: 7.8361. Min Act: -0.1700
Data Index: 4255107 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9611. Min Range: -7.9611
Max Act: 7.7736. Min Act: -0.1700
Data Index: 2788522 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9611. Min Range: -7.9611
Max Act: 7.7736. Min Act: -0.1700
Data Index: 1108009 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9611. Min Range: -7.9611
Max Act: 7.7111. Min Act: -0.1700
Data Index: 6849529 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9611. Min Range: -7.9611
Max Act: 7.6486. Min Act: -0.1700
Data Index: 1396931 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9611. Min Range: -7.9611
Max Act: 7.5861. Min Act: -0.1700
Data Index: 7660546 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9611. Min Range: -7.9611
Max Act: 7.5236. Min Act: -0.1700
Data Index: 5943377 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9611. Min Range: -7.9611
Max Act: 7.5236. Min Act: -0.1700
Data Index: 5853540 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9611. Min Range: -7.9611
Max Act: 7.4923. Min Act: -0.1700
Data Index: 3568164 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9611. Min Range: -7.9611
Max Act: 7.4611. Min Act: -0.1700
Data Index: 6694064 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9611. Min Range: -7.9611
Max Act: 7.4298. Min Act: -0.1700
Data Index: 2225539 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9611. Min Range: -7.9611
Max Act: 7.4298. Min Act: -0.1700
Data Index: 4992792 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9611. Min Range: -7.9611
Max Act: 7.3986. Min Act: -0.1700
Data Index: 4773208 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9611. Min Range: -7.9611
Max Act: 7.3986. Min Act: -0.1700
Data Index: 8181923 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9611. Min Range: -7.9611
Max Act: 7.3673. Min Act: -0.1700
Data Index: 6509147 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9611. Min Range: -7.9611
Max Act: 7.3673. Min Act: -0.1700
Data Index: 4150707 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9611. Min Range: -7.9611
Max Act: 7.3673. Min Act: -0.1700
Data Index: 4810678 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9611. Min Range: -7.9611
Max Act: 7.3673. Min Act: -0.1700
Data Index: 2246118 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9611. Min Range: -7.9611
Max Act: 7.3361. Min Act: -0.1700
Data Index: 2811452 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19