Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4062 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6140. Min Range: -6.6140
Max Act: 6.6140. Min Act: -0.1700
Data Index: 3111431 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6140. Min Range: -6.6140
Max Act: 6.1765. Min Act: -0.1700
Data Index: 2846046 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6140. Min Range: -6.6140
Max Act: 6.1140. Min Act: -0.1700
Data Index: 1284525 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6140. Min Range: -6.6140
Max Act: 6.0515. Min Act: -0.1700
Data Index: 343834 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6140. Min Range: -6.6140
Max Act: 5.9890. Min Act: -0.1700
Data Index: 5197483 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6140. Min Range: -6.6140
Max Act: 5.9890. Min Act: -0.1700
Data Index: 2195644 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6140. Min Range: -6.6140
Max Act: 5.9890. Min Act: -0.1700
Data Index: 2195646 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6140. Min Range: -6.6140
Max Act: 5.8952. Min Act: -0.1700
Data Index: 582560 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6140. Min Range: -6.6140
Max Act: 5.9577. Min Act: -0.1700
Data Index: 8493785 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6140. Min Range: -6.6140
Max Act: 5.9265. Min Act: -0.1700
Data Index: 4401176 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6140. Min Range: -6.6140
Max Act: 5.8952. Min Act: -0.1700
Data Index: 8105046 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6140. Min Range: -6.6140
Max Act: 5.8640. Min Act: -0.1700
Data Index: 8157549 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6140. Min Range: -6.6140
Max Act: 5.8952. Min Act: -0.1700
Data Index: 8783145 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6140. Min Range: -6.6140
Max Act: 5.8952. Min Act: -0.1700
Data Index: 8568529 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6140. Min Range: -6.6140
Max Act: 5.8640. Min Act: -0.1700
Data Index: 913679 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6140. Min Range: -6.6140
Max Act: 5.8640. Min Act: -0.1700
Data Index: 7158883 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6140. Min Range: -6.6140
Max Act: 5.8015. Min Act: -0.1700
Data Index: 6000729 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6140. Min Range: -6.6140
Max Act: 5.8015. Min Act: -0.1700
Data Index: 5839582 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6140. Min Range: -6.6140
Max Act: 5.8327. Min Act: -0.1700
Data Index: 6927425 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6140. Min Range: -6.6140
Max Act: 5.7390. Min Act: -0.1700
Data Index: 4493381 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19