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

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

Neuron 2836 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1487. Min Act: -0.0002

Data Index: 394831 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1416. Min Act: -0.0002

Data Index: 1039490 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1330. Min Act: -0.0002

Data Index: 461181 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1363. Min Act: -0.0002

Data Index: 377192 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1313. Min Act: -0.0002

Data Index: 927345 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1329. Min Act: -0.0002

Data Index: 617502 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1369. Min Act: -0.0002

Data Index: 445417 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1273. Min Act: -0.0002

Data Index: 1322694 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1267. Min Act: -0.0002

Data Index: 349175 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1264. Min Act: -0.0002

Data Index: 683879 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1183. Min Act: -0.0002

Data Index: 302934 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1216. Min Act: -0.0002

Data Index: 122585 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1186. Min Act: -0.0002

Data Index: 997370 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1254. Min Act: -0.0002

Data Index: 1242280 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1243. Min Act: -0.0002

Data Index: 822391 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1208. Min Act: -0.0002

Data Index: 48114 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1170. Min Act: -0.0002

Data Index: 542985 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1173. Min Act: -0.0002

Data Index: 681566 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1194. Min Act: -0.0002

Data Index: 1221610 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1227. Min Act: -0.0002

Data Index: 785087 (C4 (Web Text))

Max Activating Token Index: 527