Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2639 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7729. Min Range: -5.7729
Max Act: 5.7729. Min Act: -0.1700
Data Index: 3342705 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7729. Min Range: -5.7729
Max Act: 5.7729. Min Act: -0.1700
Data Index: 1089994 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7729. Min Range: -5.7729
Max Act: 5.7417. Min Act: -0.1700
Data Index: 8105814 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7729. Min Range: -5.7729
Max Act: 5.7417. Min Act: -0.1700
Data Index: 5817046 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7729. Min Range: -5.7729
Max Act: 5.6792. Min Act: -0.1700
Data Index: 5227118 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7729. Min Range: -5.7729
Max Act: 5.6479. Min Act: -0.1700
Data Index: 3351043 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7729. Min Range: -5.7729
Max Act: 5.5854. Min Act: -0.1700
Data Index: 1661466 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7729. Min Range: -5.7729
Max Act: 5.5854. Min Act: -0.1700
Data Index: 7474569 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7729. Min Range: -5.7729
Max Act: 5.5229. Min Act: -0.1700
Data Index: 6426381 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7729. Min Range: -5.7729
Max Act: 5.5542. Min Act: -0.1700
Data Index: 8546599 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7729. Min Range: -5.7729
Max Act: 5.4917. Min Act: -0.1700
Data Index: 2370879 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7729. Min Range: -5.7729
Max Act: 5.4917. Min Act: -0.1700
Data Index: 3449464 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7729. Min Range: -5.7729
Max Act: 5.4917. Min Act: -0.1700
Data Index: 1326076 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7729. Min Range: -5.7729
Max Act: 5.4292. Min Act: -0.1700
Data Index: 6967010 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7729. Min Range: -5.7729
Max Act: 5.4292. Min Act: -0.1700
Data Index: 6828713 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7729. Min Range: -5.7729
Max Act: 5.3979. Min Act: -0.1700
Data Index: 4317003 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7729. Min Range: -5.7729
Max Act: 5.3979. Min Act: -0.1700
Data Index: 1425065 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7729. Min Range: -5.7729
Max Act: 5.3667. Min Act: -0.1700
Data Index: 5267852 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7729. Min Range: -5.7729
Max Act: 5.3667. Min Act: -0.1700
Data Index: 6798648 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7729. Min Range: -5.7729
Max Act: 5.3667. Min Act: -0.1700
Data Index: 2557167 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19