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

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

Neuron 980 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5357. Min Range: -2.5357

Max Act: 2.5357. Min Act: -0.0000

Data Index: 1084345 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 2.5357. Min Range: -2.5357

Max Act: 2.2334. Min Act: -0.0000

Data Index: 421655 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 2.5357. Min Range: -2.5357

Max Act: 2.2529. Min Act: -0.0000

Data Index: 1039836 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 2.5357. Min Range: -2.5357

Max Act: 2.4164. Min Act: -0.0000

Data Index: 1312981 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 2.5357. Min Range: -2.5357

Max Act: 2.2544. Min Act: -0.0000

Data Index: 1149320 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 2.5357. Min Range: -2.5357

Max Act: 2.4917. Min Act: -0.0001

Data Index: 404083 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 2.5357. Min Range: -2.5357

Max Act: 2.0762. Min Act: -0.0001

Data Index: 269157 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 2.5357. Min Range: -2.5357

Max Act: 2.3165. Min Act: -0.0001

Data Index: 1092440 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 2.5357. Min Range: -2.5357

Max Act: 2.0729. Min Act: -0.0000

Data Index: 1339402 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 2.5357. Min Range: -2.5357

Max Act: 2.0478. Min Act: -0.0000

Data Index: 824264 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 2.5357. Min Range: -2.5357

Max Act: 2.0262. Min Act: -0.0000

Data Index: 1303002 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 2.5357. Min Range: -2.5357

Max Act: 2.0829. Min Act: -0.0000

Data Index: 235879 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 2.5357. Min Range: -2.5357

Max Act: 2.0105. Min Act: -0.0000

Data Index: 1354351 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 2.5357. Min Range: -2.5357

Max Act: 2.0756. Min Act: -0.0001

Data Index: 1295113 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 2.5357. Min Range: -2.5357

Max Act: 1.8590. Min Act: -0.0000

Data Index: 627940 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 2.5357. Min Range: -2.5357

Max Act: 2.0552. Min Act: -0.0000

Data Index: 1104040 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 2.5357. Min Range: -2.5357

Max Act: 2.0921. Min Act: -0.0000

Data Index: 495855 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 2.5357. Min Range: -2.5357

Max Act: 1.7884. Min Act: -0.0000

Data Index: 959976 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 2.5357. Min Range: -2.5357

Max Act: 1.7973. Min Act: -0.0001

Data Index: 807059 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 2.5357. Min Range: -2.5357

Max Act: 1.9693. Min Act: -0.0000

Data Index: 1314238 (C4 (Web Text))

Max Activating Token Index: 562