Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 765 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0798. Min Range: -8.0798
Max Act: 8.0798. Min Act: -0.1699
Data Index: 1201891 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0798. Min Range: -8.0798
Max Act: 7.8298. Min Act: -0.1700
Data Index: 14611 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0798. Min Range: -8.0798
Max Act: 7.7673. Min Act: -0.1700
Data Index: 8019693 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0798. Min Range: -8.0798
Max Act: 7.7048. Min Act: -0.1700
Data Index: 7771612 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0798. Min Range: -8.0798
Max Act: 7.6423. Min Act: -0.1700
Data Index: 1623865 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0798. Min Range: -8.0798
Max Act: 7.6736. Min Act: -0.1700
Data Index: 5625146 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0798. Min Range: -8.0798
Max Act: 7.5486. Min Act: -0.1700
Data Index: 1204172 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0798. Min Range: -8.0798
Max Act: 7.5173. Min Act: -0.1700
Data Index: 8000800 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0798. Min Range: -8.0798
Max Act: 7.5486. Min Act: -0.1700
Data Index: 2974688 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0798. Min Range: -8.0798
Max Act: 7.5486. Min Act: -0.1700
Data Index: 3702351 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0798. Min Range: -8.0798
Max Act: 7.5173. Min Act: -0.1700
Data Index: 4948027 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0798. Min Range: -8.0798
Max Act: 7.5173. Min Act: -0.1700
Data Index: 1622577 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0798. Min Range: -8.0798
Max Act: 7.4861. Min Act: -0.1700
Data Index: 5596051 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0798. Min Range: -8.0798
Max Act: 7.4548. Min Act: -0.1700
Data Index: 2594723 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0798. Min Range: -8.0798
Max Act: 7.4861. Min Act: -0.1700
Data Index: 4586373 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0798. Min Range: -8.0798
Max Act: 7.4548. Min Act: -0.1700
Data Index: 3091072 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0798. Min Range: -8.0798
Max Act: 7.4861. Min Act: -0.1700
Data Index: 3643169 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0798. Min Range: -8.0798
Max Act: 7.4548. Min Act: -0.1700
Data Index: 4149731 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0798. Min Range: -8.0798
Max Act: 7.3923. Min Act: -0.1700
Data Index: 6728079 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0798. Min Range: -8.0798
Max Act: 7.3611. Min Act: -0.1700
Data Index: 2014124 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19