Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4170 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1015537 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0441. Min Act: -0.0002

Data Index: 701788 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0406. Min Act: -0.0002

Data Index: 42339 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0370. Min Act: -0.0002

Data Index: 928800 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0384. Min Act: -0.0002

Data Index: 1245202 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1239058 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1219644 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0358. Min Act: -0.0002

Data Index: 665035 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0353. Min Act: -0.0002

Data Index: 997058 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0375. Min Act: -0.0002

Data Index: 47191 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0352. Min Act: -0.0002

Data Index: 624535 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0360. Min Act: -0.0002

Data Index: 844849 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0351. Min Act: -0.0002

Data Index: 62086 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0352. Min Act: -0.0002

Data Index: 1200850 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1211822 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0364. Min Act: -0.0002

Data Index: 24730 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0353. Min Act: -0.0002

Data Index: 1137224 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0349. Min Act: -0.0002

Data Index: 599563 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0355. Min Act: -0.0002

Data Index: 367878 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1048586 (C4 (Web Text))

Max Activating Token Index: 522