Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 396 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0462. Min Act: -0.0002

Data Index: 529078 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0449. Min Act: -0.0002

Data Index: 874674 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1197739 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0417. Min Act: -0.0002

Data Index: 290833 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0414. Min Act: -0.0002

Data Index: 244206 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0421. Min Act: -0.0002

Data Index: 1027728 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1355086 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0400. Min Act: -0.0002

Data Index: 189415 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0394. Min Act: -0.0002

Data Index: 12381 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1035249 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0397. Min Act: -0.0002

Data Index: 284538 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1141335 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0398. Min Act: -0.0002

Data Index: 483335 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0415. Min Act: -0.0002

Data Index: 346479 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0404. Min Act: -0.0002

Data Index: 507690 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0404. Min Act: -0.0002

Data Index: 529733 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0391. Min Act: -0.0002

Data Index: 838343 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0384. Min Act: -0.0002

Data Index: 547057 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0395. Min Act: -0.0002

Data Index: 128239 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0404. Min Act: -0.0002

Data Index: 974775 (C4 (Web Text))

Max Activating Token Index: 663