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

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

Neuron 3754 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: 0.2187. Min Range: -0.2187

Max Act: 0.2187. Min Act: -0.0001

Data Index: 936856 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.2187. Min Range: -0.2187

Max Act: 0.1850. Min Act: -0.0001

Data Index: 846930 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 0.2187. Min Range: -0.2187

Max Act: 0.1876. Min Act: -0.0001

Data Index: 941713 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.2187. Min Range: -0.2187

Max Act: 0.1799. Min Act: -0.0001

Data Index: 503168 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 0.2187. Min Range: -0.2187

Max Act: 0.1738. Min Act: -0.0001

Data Index: 738671 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.2187. Min Range: -0.2187

Max Act: 0.1632. Min Act: -0.0001

Data Index: 70264 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.2187. Min Range: -0.2187

Max Act: 0.1509. Min Act: -0.0001

Data Index: 1253698 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.2187. Min Range: -0.2187

Max Act: 0.1301. Min Act: -0.0001

Data Index: 956698 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 0.2187. Min Range: -0.2187

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1108352 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.2187. Min Range: -0.2187

Max Act: 0.1342. Min Act: -0.0001

Data Index: 94018 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.2187. Min Range: -0.2187

Max Act: 0.1383. Min Act: -0.0001

Data Index: 358750 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.2187. Min Range: -0.2187

Max Act: 0.1304. Min Act: -0.0001

Data Index: 775919 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 0.2187. Min Range: -0.2187

Max Act: 0.1317. Min Act: -0.0001

Data Index: 876576 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.2187. Min Range: -0.2187

Max Act: 0.1306. Min Act: -0.0001

Data Index: 332846 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.2187. Min Range: -0.2187

Max Act: 0.1308. Min Act: -0.0001

Data Index: 577032 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 0.2187. Min Range: -0.2187

Max Act: 0.1158. Min Act: -0.0001

Data Index: 284566 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 0.2187. Min Range: -0.2187

Max Act: 0.1172. Min Act: -0.0001

Data Index: 1196912 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.2187. Min Range: -0.2187

Max Act: 0.1313. Min Act: -0.0001

Data Index: 225811 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 0.2187. Min Range: -0.2187

Max Act: 0.1193. Min Act: -0.0001

Data Index: 299595 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.2187. Min Range: -0.2187

Max Act: 0.1272. Min Act: -0.0001

Data Index: 972563 (C4 (Web Text))

Max Activating Token Index: 709