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

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

Neuron 2179 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: 1.0245. Min Range: -1.0245

Max Act: 1.0245. Min Act: -0.0000

Data Index: 675552 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.8693. Min Act: -0.0000

Data Index: 981156 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.8241. Min Act: -0.0000

Data Index: 276013 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.7601. Min Act: -0.0000

Data Index: 463013 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.7822. Min Act: -0.0000

Data Index: 530145 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.7784. Min Act: -0.0000

Data Index: 1239395 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.7301. Min Act: -0.0000

Data Index: 678087 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.7053. Min Act: -0.0000

Data Index: 795024 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.7171. Min Act: -0.0000

Data Index: 469520 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.6751. Min Act: -0.0000

Data Index: 95791 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.6224. Min Act: -0.0000

Data Index: 516070 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.6180. Min Act: -0.0000

Data Index: 186669 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1159946 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.6872. Min Act: -0.0000

Data Index: 312562 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.6006. Min Act: -0.0000

Data Index: 1596016 (Python Code)

Max Activating Token Index: 15

Text #15

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.6377. Min Act: -0.0000

Data Index: 791551 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1109443 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.5904. Min Act: -0.0000

Data Index: 1182905 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.5517. Min Act: -0.0000

Data Index: 577055 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 1.0245. Min Range: -1.0245

Max Act: 0.5721. Min Act: -0.0000

Data Index: 1043365 (C4 (Web Text))

Max Activating Token Index: 905