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

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

Neuron 1687 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1293062 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1634. Min Act: -0.0001

Data Index: 589910 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1538. Min Act: -0.0000

Data Index: 249006 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1515. Min Act: -0.0000

Data Index: 443148 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1430. Min Act: -0.0000

Data Index: 823534 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1416. Min Act: -0.0001

Data Index: 372839 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1359. Min Act: -0.0001

Data Index: 361964 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1302. Min Act: -0.0000

Data Index: 866618 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1336. Min Act: -0.0000

Data Index: 1329889 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1326. Min Act: -0.0000

Data Index: 1133807 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1367. Min Act: -0.0001

Data Index: 435375 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1289. Min Act: -0.0001

Data Index: 1332483 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1246. Min Act: -0.0000

Data Index: 305402 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1263. Min Act: -0.0001

Data Index: 240337 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1214. Min Act: -0.0000

Data Index: 1358638 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1258. Min Act: -0.0000

Data Index: 935210 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1203. Min Act: -0.0000

Data Index: 1251973 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1338521 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1315087 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1218. Min Act: -0.0000

Data Index: 1030775 (C4 (Web Text))

Max Activating Token Index: 97