Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2631 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0335. Min Act: -0.0001

Data Index: 748828 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0300. Min Act: -0.0001

Data Index: 1527643 (Python Code)

Max Activating Token Index: 722

Text #2

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0286. Min Act: -0.0001

Data Index: 106561 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0302. Min Act: -0.0001

Data Index: 1312200 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0298. Min Act: -0.0001

Data Index: 382802 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1327078 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0311. Min Act: -0.0001

Data Index: 1574319 (Python Code)

Max Activating Token Index: 693

Text #7

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0292. Min Act: -0.0001

Data Index: 1010204 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0279. Min Act: -0.0001

Data Index: 903228 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0296. Min Act: -0.0002

Data Index: 507484 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0312. Min Act: -0.0001

Data Index: 642926 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0310. Min Act: -0.0001

Data Index: 1262206 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0297. Min Act: -0.0001

Data Index: 1632630 (Python Code)

Max Activating Token Index: 177

Text #13

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0292. Min Act: -0.0001

Data Index: 1110575 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0291. Min Act: -0.0001

Data Index: 691176 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0288. Min Act: -0.0001

Data Index: 1608022 (Python Code)

Max Activating Token Index: 924

Text #16

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0306. Min Act: -0.0001

Data Index: 1439822 (Python Code)

Max Activating Token Index: 235

Text #17

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0285. Min Act: -0.0001

Data Index: 830439 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0291. Min Act: -0.0001

Data Index: 820437 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0288. Min Act: -0.0001

Data Index: 48843 (C4 (Web Text))

Max Activating Token Index: 302