Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3679 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1535351 (Python Code)

Max Activating Token Index: 560

Text #1

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1908. Min Act: -0.0000

Data Index: 1600028 (Python Code)

Max Activating Token Index: 510

Text #2

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1504. Min Act: -0.0000

Data Index: 1651731 (Python Code)

Max Activating Token Index: 713

Text #3

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1338. Min Act: -0.0000

Data Index: 1599462 (Python Code)

Max Activating Token Index: 273

Text #4

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1209. Min Act: -0.0000

Data Index: 1479348 (Python Code)

Max Activating Token Index: 936

Text #5

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1245. Min Act: -0.0000

Data Index: 958818 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1293. Min Act: -0.0000

Data Index: 1504385 (Python Code)

Max Activating Token Index: 567

Text #7

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1521921 (Python Code)

Max Activating Token Index: 478

Text #8

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1334. Min Act: -0.0000

Data Index: 1614037 (Python Code)

Max Activating Token Index: 728

Text #9

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1221. Min Act: -0.0000

Data Index: 1506506 (Python Code)

Max Activating Token Index: 262

Text #10

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1467939 (Python Code)

Max Activating Token Index: 567

Text #11

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1221. Min Act: -0.0000

Data Index: 1365291 (Python Code)

Max Activating Token Index: 542

Text #12

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1197. Min Act: -0.0000

Data Index: 1506523 (Python Code)

Max Activating Token Index: 697

Text #13

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1169. Min Act: -0.0000

Data Index: 1379843 (Python Code)

Max Activating Token Index: 202

Text #14

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1187. Min Act: -0.0000

Data Index: 1625293 (Python Code)

Max Activating Token Index: 1010

Text #15

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1303. Min Act: -0.0000

Data Index: 1508167 (Python Code)

Max Activating Token Index: 372

Text #16

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1176. Min Act: -0.0000

Data Index: 1456786 (Python Code)

Max Activating Token Index: 633

Text #17

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1624764 (Python Code)

Max Activating Token Index: 696

Text #18

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1101. Min Act: -0.0000

Data Index: 1420502 (Python Code)

Max Activating Token Index: 818

Text #19

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1145. Min Act: -0.0000

Data Index: 1500469 (Python Code)

Max Activating Token Index: 140