Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4062 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.7398. Min Act: -0.0000

Data Index: 1203831 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.7459. Min Act: -0.0000

Data Index: 1299074 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.6301. Min Act: 0.0000

Data Index: 637106 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.6236. Min Act: -0.0000

Data Index: 1037065 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.6015. Min Act: -0.0000

Data Index: 561922 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5807. Min Act: -0.0000

Data Index: 291706 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5437. Min Act: -0.0000

Data Index: 79335 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5234. Min Act: -0.0000

Data Index: 158396 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5370. Min Act: -0.0000

Data Index: 82555 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5322. Min Act: -0.0000

Data Index: 1185038 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5184. Min Act: -0.0000

Data Index: 450035 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5481. Min Act: -0.0000

Data Index: 445961 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5278. Min Act: -0.0000

Data Index: 907431 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5250. Min Act: -0.0000

Data Index: 364337 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5300. Min Act: -0.0000

Data Index: 531855 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5133. Min Act: -0.0000

Data Index: 994114 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.5109. Min Act: 0.0000

Data Index: 1200028 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.4659. Min Act: -0.0000

Data Index: 533085 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.4644. Min Act: -0.0000

Data Index: 1025243 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.7459. Min Range: -0.7459

Max Act: 0.4747. Min Act: -0.0000

Data Index: 115189 (C4 (Web Text))

Max Activating Token Index: 462