Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6358 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5111. Min Range: -6.5111
Max Act: 6.5111. Min Act: -0.1700
Data Index: 8064010 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5111. Min Range: -6.5111
Max Act: 6.3236. Min Act: -0.1700
Data Index: 1200658 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5111. Min Range: -6.5111
Max Act: 6.2923. Min Act: -0.1700
Data Index: 4566451 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5111. Min Range: -6.5111
Max Act: 6.2923. Min Act: -0.1700
Data Index: 676837 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5111. Min Range: -6.5111
Max Act: 6.1986. Min Act: -0.1700
Data Index: 8545471 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5111. Min Range: -6.5111
Max Act: 6.1673. Min Act: -0.1700
Data Index: 654026 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5111. Min Range: -6.5111
Max Act: 6.0736. Min Act: -0.1700
Data Index: 6845211 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5111. Min Range: -6.5111
Max Act: 6.0423. Min Act: -0.1700
Data Index: 169995 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5111. Min Range: -6.5111
Max Act: 6.0736. Min Act: -0.1700
Data Index: 7450106 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5111. Min Range: -6.5111
Max Act: 6.0736. Min Act: -0.1700
Data Index: 7900089 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5111. Min Range: -6.5111
Max Act: 6.0111. Min Act: -0.1700
Data Index: 6202817 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5111. Min Range: -6.5111
Max Act: 6.0423. Min Act: -0.1700
Data Index: 7429468 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5111. Min Range: -6.5111
Max Act: 6.0423. Min Act: -0.1700
Data Index: 8762614 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5111. Min Range: -6.5111
Max Act: 6.0423. Min Act: -0.1700
Data Index: 6429781 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5111. Min Range: -6.5111
Max Act: 6.0111. Min Act: -0.1700
Data Index: 1262508 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5111. Min Range: -6.5111
Max Act: 5.9798. Min Act: -0.1700
Data Index: 6321553 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5111. Min Range: -6.5111
Max Act: 5.9798. Min Act: -0.1700
Data Index: 4137942 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5111. Min Range: -6.5111
Max Act: 6.0111. Min Act: -0.1700
Data Index: 4776821 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5111. Min Range: -6.5111
Max Act: 6.0111. Min Act: -0.1700
Data Index: 3736078 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5111. Min Range: -6.5111
Max Act: 5.9798. Min Act: -0.1700
Data Index: 2539878 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19