Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4245 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1298. Min Range: -7.1298
Max Act: 7.1298. Min Act: -0.1700
Data Index: 3067524 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1298. Min Range: -7.1298
Max Act: 7.0361. Min Act: -0.1700
Data Index: 2157436 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1298. Min Range: -7.1298
Max Act: 7.0048. Min Act: -0.1700
Data Index: 5609264 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1298. Min Range: -7.1298
Max Act: 6.9111. Min Act: -0.1700
Data Index: 767884 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1298. Min Range: -7.1298
Max Act: 6.9111. Min Act: -0.1700
Data Index: 4671241 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1298. Min Range: -7.1298
Max Act: 6.8798. Min Act: -0.1700
Data Index: 1449540 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1298. Min Range: -7.1298
Max Act: 6.7861. Min Act: -0.1700
Data Index: 1057322 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1298. Min Range: -7.1298
Max Act: 6.7861. Min Act: -0.1700
Data Index: 8111714 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1298. Min Range: -7.1298
Max Act: 6.7861. Min Act: -0.1700
Data Index: 4560542 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1298. Min Range: -7.1298
Max Act: 6.6611. Min Act: -0.1700
Data Index: 6804696 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1298. Min Range: -7.1298
Max Act: 6.6923. Min Act: -0.1700
Data Index: 2690432 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1298. Min Range: -7.1298
Max Act: 6.6923. Min Act: -0.1700
Data Index: 7268333 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1298. Min Range: -7.1298
Max Act: 6.6923. Min Act: -0.1700
Data Index: 3538615 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1298. Min Range: -7.1298
Max Act: 6.6923. Min Act: -0.1700
Data Index: 4969053 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1298. Min Range: -7.1298
Max Act: 6.6611. Min Act: -0.1700
Data Index: 4545752 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1298. Min Range: -7.1298
Max Act: 6.6298. Min Act: -0.1700
Data Index: 5487054 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1298. Min Range: -7.1298
Max Act: 6.6298. Min Act: -0.1700
Data Index: 5714942 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1298. Min Range: -7.1298
Max Act: 6.5673. Min Act: -0.1700
Data Index: 4647346 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1298. Min Range: -7.1298
Max Act: 6.5673. Min Act: -0.1700
Data Index: 948381 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1298. Min Range: -7.1298
Max Act: 6.5673. Min Act: -0.1700
Data Index: 5661260 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19