Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1651 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0416. Min Act: -0.0003

Data Index: 936543 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0406. Min Act: -0.0003

Data Index: 247597 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0402. Min Act: -0.0002

Data Index: 239417 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0414. Min Act: -0.0003

Data Index: 783339 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0361. Min Act: -0.0002

Data Index: 18899 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0391. Min Act: -0.0003

Data Index: 2891 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0378. Min Act: -0.0003

Data Index: 1215679 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0344. Min Act: -0.0003

Data Index: 967983 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0359. Min Act: -0.0004

Data Index: 999634 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0349. Min Act: -0.0003

Data Index: 782470 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0373. Min Act: -0.0004

Data Index: 217922 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0359. Min Act: -0.0003

Data Index: 1226162 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0342. Min Act: -0.0004

Data Index: 1096191 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0349. Min Act: -0.0003

Data Index: 1182741 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0361. Min Act: -0.0003

Data Index: 891676 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0325. Min Act: -0.0003

Data Index: 828847 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0373. Min Act: -0.0003

Data Index: 451474 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0339. Min Act: -0.0003

Data Index: 441200 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0354. Min Act: -0.0003

Data Index: 765351 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0331. Min Act: -0.0003

Data Index: 665879 (C4 (Web Text))

Max Activating Token Index: 443