Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4915 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2173. Min Range: -7.2173
Max Act: 7.2173. Min Act: -0.1700
Data Index: 2558538 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2173. Min Range: -7.2173
Max Act: 7.2173. Min Act: -0.1700
Data Index: 8448135 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2173. Min Range: -7.2173
Max Act: 7.1236. Min Act: -0.1700
Data Index: 8023007 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2173. Min Range: -7.2173
Max Act: 7.0923. Min Act: -0.1700
Data Index: 3715091 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2173. Min Range: -7.2173
Max Act: 6.9361. Min Act: -0.1700
Data Index: 1788569 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2173. Min Range: -7.2173
Max Act: 6.9361. Min Act: -0.1700
Data Index: 3055798 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2173. Min Range: -7.2173
Max Act: 6.8736. Min Act: -0.1700
Data Index: 6016008 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2173. Min Range: -7.2173
Max Act: 6.8111. Min Act: -0.1700
Data Index: 7282303 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2173. Min Range: -7.2173
Max Act: 6.7798. Min Act: -0.1700
Data Index: 7863979 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2173. Min Range: -7.2173
Max Act: 6.7798. Min Act: -0.1700
Data Index: 4175652 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2173. Min Range: -7.2173
Max Act: 6.7486. Min Act: -0.1700
Data Index: 7545037 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2173. Min Range: -7.2173
Max Act: 6.7486. Min Act: -0.1700
Data Index: 3402450 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2173. Min Range: -7.2173
Max Act: 6.7173. Min Act: -0.1700
Data Index: 5470814 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2173. Min Range: -7.2173
Max Act: 6.7173. Min Act: -0.1700
Data Index: 254985 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2173. Min Range: -7.2173
Max Act: 6.7173. Min Act: -0.1700
Data Index: 4911815 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2173. Min Range: -7.2173
Max Act: 6.6548. Min Act: -0.1700
Data Index: 142824 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2173. Min Range: -7.2173
Max Act: 6.6861. Min Act: -0.1700
Data Index: 6393081 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2173. Min Range: -7.2173
Max Act: 6.6861. Min Act: -0.1700
Data Index: 4071499 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2173. Min Range: -7.2173
Max Act: 6.6861. Min Act: -0.1700
Data Index: 6101164 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2173. Min Range: -7.2173
Max Act: 6.6548. Min Act: -0.1700
Data Index: 1710738 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19