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

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

Neuron 4309 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1534. Min Act: -0.0002

Data Index: 810731 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1451. Min Act: -0.0002

Data Index: 777149 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1424. Min Act: -0.0002

Data Index: 419995 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1388. Min Act: -0.0002

Data Index: 642359 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1334. Min Act: -0.0002

Data Index: 1326373 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1353. Min Act: -0.0002

Data Index: 679056 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1339. Min Act: -0.0002

Data Index: 1042934 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1338. Min Act: -0.0002

Data Index: 771963 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1394. Min Act: -0.0002

Data Index: 879126 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1254. Min Act: -0.0002

Data Index: 22163 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1368. Min Act: -0.0002

Data Index: 493859 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1231. Min Act: -0.0002

Data Index: 404135 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1257. Min Act: -0.0002

Data Index: 1134278 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1258. Min Act: -0.0002

Data Index: 824896 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1286. Min Act: -0.0002

Data Index: 1301912 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1261. Min Act: -0.0002

Data Index: 1285113 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1135. Min Act: -0.0002

Data Index: 75711 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1232. Min Act: -0.0002

Data Index: 1292214 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1158. Min Act: -0.0002

Data Index: 54442 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 0.1534. Min Range: -0.1534

Max Act: 0.1181. Min Act: -0.0002

Data Index: 148103 (C4 (Web Text))

Max Activating Token Index: 137