Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2891 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7173. Min Range: -8.7173
Max Act: 8.7173. Min Act: -0.1700
Data Index: 8346423 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7173. Min Range: -8.7173
Max Act: 8.2173. Min Act: -0.1700
Data Index: 7837032 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7173. Min Range: -8.7173
Max Act: 8.1548. Min Act: -0.1700
Data Index: 1263532 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7173. Min Range: -8.7173
Max Act: 8.1548. Min Act: -0.1700
Data Index: 8135724 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7173. Min Range: -8.7173
Max Act: 8.0923. Min Act: -0.1700
Data Index: 7131617 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7173. Min Range: -8.7173
Max Act: 8.0923. Min Act: -0.1700
Data Index: 1346829 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7173. Min Range: -8.7173
Max Act: 8.0923. Min Act: -0.1700
Data Index: 2911298 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7173. Min Range: -8.7173
Max Act: 8.0923. Min Act: -0.1700
Data Index: 5906575 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7173. Min Range: -8.7173
Max Act: 8.0923. Min Act: -0.1700
Data Index: 2504661 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7173. Min Range: -8.7173
Max Act: 8.0298. Min Act: -0.1700
Data Index: 828404 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7173. Min Range: -8.7173
Max Act: 8.0298. Min Act: -0.1700
Data Index: 708895 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7173. Min Range: -8.7173
Max Act: 7.9673. Min Act: -0.1700
Data Index: 5741576 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7173. Min Range: -8.7173
Max Act: 7.9673. Min Act: -0.1700
Data Index: 8321597 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7173. Min Range: -8.7173
Max Act: 7.9048. Min Act: -0.1700
Data Index: 6370903 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7173. Min Range: -8.7173
Max Act: 7.9048. Min Act: -0.1700
Data Index: 2261089 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7173. Min Range: -8.7173
Max Act: 7.9048. Min Act: -0.1700
Data Index: 5879289 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7173. Min Range: -8.7173
Max Act: 7.8423. Min Act: -0.1700
Data Index: 1434731 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7173. Min Range: -8.7173
Max Act: 7.9048. Min Act: -0.1700
Data Index: 4929790 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7173. Min Range: -8.7173
Max Act: 7.8423. Min Act: -0.1700
Data Index: 7714889 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7173. Min Range: -8.7173
Max Act: 7.8423. Min Act: -0.1700
Data Index: 7817737 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19