Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4953 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9861. Min Range: -7.9861
Max Act: 7.9861. Min Act: -0.1700
Data Index: 5755645 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9861. Min Range: -7.9861
Max Act: 7.8611. Min Act: -0.1700
Data Index: 8110097 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9861. Min Range: -7.9861
Max Act: 7.6736. Min Act: -0.1700
Data Index: 5343639 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9861. Min Range: -7.9861
Max Act: 7.7049. Min Act: -0.1700
Data Index: 7028796 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9861. Min Range: -7.9861
Max Act: 7.6424. Min Act: -0.1700
Data Index: 1911736 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9861. Min Range: -7.9861
Max Act: 7.6111. Min Act: -0.1700
Data Index: 5162683 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9861. Min Range: -7.9861
Max Act: 7.6424. Min Act: -0.1700
Data Index: 3716915 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9861. Min Range: -7.9861
Max Act: 7.6111. Min Act: -0.1700
Data Index: 5201909 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9861. Min Range: -7.9861
Max Act: 7.5486. Min Act: -0.1700
Data Index: 3966500 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9861. Min Range: -7.9861
Max Act: 7.5486. Min Act: -0.1700
Data Index: 6501101 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9861. Min Range: -7.9861
Max Act: 7.4861. Min Act: -0.1700
Data Index: 2746515 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9861. Min Range: -7.9861
Max Act: 7.4549. Min Act: -0.1700
Data Index: 4565115 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9861. Min Range: -7.9861
Max Act: 7.4236. Min Act: -0.1700
Data Index: 1684620 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9861. Min Range: -7.9861
Max Act: 7.4236. Min Act: -0.1700
Data Index: 4523140 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9861. Min Range: -7.9861
Max Act: 7.3924. Min Act: -0.1700
Data Index: 2600876 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9861. Min Range: -7.9861
Max Act: 7.3611. Min Act: -0.1700
Data Index: 7948538 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9861. Min Range: -7.9861
Max Act: 7.2986. Min Act: -0.1700
Data Index: 6583428 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9861. Min Range: -7.9861
Max Act: 7.2674. Min Act: -0.1700
Data Index: 5101087 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9861. Min Range: -7.9861
Max Act: 7.2986. Min Act: -0.1700
Data Index: 1384207 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9861. Min Range: -7.9861
Max Act: 7.2986. Min Act: -0.1700
Data Index: 5862483 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19