Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6382 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0829. Min Range: -8.0829
Max Act: 8.0829. Min Act: -0.1700
Data Index: 8488234 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.9579. Min Act: -0.1700
Data Index: 3864136 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.9266. Min Act: -0.1700
Data Index: 1138699 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.7079. Min Act: -0.1700
Data Index: 5177545 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.6454. Min Act: -0.1700
Data Index: 1023325 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.6454. Min Act: -0.1700
Data Index: 4239044 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.6454. Min Act: -0.1700
Data Index: 4191108 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.5516. Min Act: -0.1700
Data Index: 3487306 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.5516. Min Act: -0.1700
Data Index: 5623331 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.4891. Min Act: -0.1700
Data Index: 6254016 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.5516. Min Act: -0.1700
Data Index: 669059 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.5204. Min Act: -0.1700
Data Index: 2985893 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.5204. Min Act: -0.1700
Data Index: 942124 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.5204. Min Act: -0.1700
Data Index: 7474653 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.4891. Min Act: -0.1700
Data Index: 6450141 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.4891. Min Act: -0.1700
Data Index: 7946105 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.4891. Min Act: -0.1700
Data Index: 6438985 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.4579. Min Act: -0.1700
Data Index: 5707789 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.4579. Min Act: -0.1700
Data Index: 4195294 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.3954. Min Act: -0.1700
Data Index: 4098393 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19