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

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

Neuron 3456 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1379. Min Range: -1.1379

Max Act: 1.1379. Min Act: -0.0002

Data Index: 186329 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 1.1379. Min Range: -1.1379

Max Act: 1.1376. Min Act: -0.0002

Data Index: 515182 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 1.1379. Min Range: -1.1379

Max Act: 1.1114. Min Act: -0.0002

Data Index: 1355269 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 1.1379. Min Range: -1.1379

Max Act: 1.1177. Min Act: -0.0002

Data Index: 980832 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 1.1379. Min Range: -1.1379

Max Act: 1.0937. Min Act: -0.0002

Data Index: 475323 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 1.1379. Min Range: -1.1379

Max Act: 1.0887. Min Act: -0.0002

Data Index: 540050 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 1.1379. Min Range: -1.1379

Max Act: 1.0725. Min Act: -0.0002

Data Index: 1357132 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 1.1379. Min Range: -1.1379

Max Act: 1.0977. Min Act: -0.0002

Data Index: 1154915 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 1.1379. Min Range: -1.1379

Max Act: 1.0680. Min Act: -0.0002

Data Index: 545454 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 1.1379. Min Range: -1.1379

Max Act: 1.0599. Min Act: -0.0002

Data Index: 259279 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 1.1379. Min Range: -1.1379

Max Act: 1.0772. Min Act: -0.0002

Data Index: 45216 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 1.1379. Min Range: -1.1379

Max Act: 1.0585. Min Act: -0.0002

Data Index: 913168 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 1.1379. Min Range: -1.1379

Max Act: 1.0616. Min Act: -0.0002

Data Index: 188777 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 1.1379. Min Range: -1.1379

Max Act: 1.0611. Min Act: -0.0002

Data Index: 149370 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 1.1379. Min Range: -1.1379

Max Act: 1.0496. Min Act: -0.0002

Data Index: 480631 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 1.1379. Min Range: -1.1379

Max Act: 1.0540. Min Act: -0.0002

Data Index: 995898 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 1.1379. Min Range: -1.1379

Max Act: 1.0456. Min Act: -0.0002

Data Index: 648690 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 1.1379. Min Range: -1.1379

Max Act: 1.0349. Min Act: -0.0002

Data Index: 994247 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 1.1379. Min Range: -1.1379

Max Act: 1.0566. Min Act: -0.0002

Data Index: 788726 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 1.1379. Min Range: -1.1379

Max Act: 1.0553. Min Act: -0.0002

Data Index: 796204 (C4 (Web Text))

Max Activating Token Index: 662