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

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

Neuron 812 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1740. Min Act: -0.0001

Data Index: 408220 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1595. Min Act: -0.0001

Data Index: 761748 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1139365 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1521. Min Act: -0.0001

Data Index: 543281 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1542. Min Act: -0.0001

Data Index: 640513 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1317. Min Act: -0.0001

Data Index: 588465 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1281. Min Act: -0.0001

Data Index: 1221977 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1405. Min Act: -0.0001

Data Index: 426456 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1362. Min Act: -0.0001

Data Index: 184085 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1315. Min Act: -0.0001

Data Index: 1250371 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1348. Min Act: -0.0001

Data Index: 211706 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1239. Min Act: -0.0001

Data Index: 276907 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1241. Min Act: -0.0001

Data Index: 978730 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1249. Min Act: -0.0001

Data Index: 788301 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1236. Min Act: -0.0001

Data Index: 180519 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1162. Min Act: -0.0001

Data Index: 1205122 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1244. Min Act: -0.0001

Data Index: 1013920 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1199. Min Act: -0.0001

Data Index: 1256504 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1253. Min Act: -0.0001

Data Index: 1292708 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1186. Min Act: -0.0001

Data Index: 738179 (C4 (Web Text))

Max Activating Token Index: 171