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

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

Neuron 4731 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.2061. Min Act: -0.0000

Data Index: 1168912 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1741. Min Act: -0.0000

Data Index: 65786 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1666. Min Act: -0.0000

Data Index: 1516132 (Python Code)

Max Activating Token Index: 500

Text #3

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1486. Min Act: -0.0000

Data Index: 1165706 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1498. Min Act: -0.0000

Data Index: 638520 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1609. Min Act: -0.0000

Data Index: 1655230 (Python Code)

Max Activating Token Index: 677

Text #6

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1432. Min Act: -0.0000

Data Index: 458240 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1404. Min Act: -0.0000

Data Index: 544105 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1354. Min Act: -0.0000

Data Index: 653582 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1383. Min Act: -0.0000

Data Index: 103863 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1313. Min Act: -0.0000

Data Index: 1053477 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1344. Min Act: -0.0000

Data Index: 801166 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1358. Min Act: -0.0000

Data Index: 124208 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1264. Min Act: -0.0000

Data Index: 14015 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1180. Min Act: -0.0000

Data Index: 216923 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1259. Min Act: -0.0000

Data Index: 780090 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1245. Min Act: -0.0000

Data Index: 934449 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1283. Min Act: -0.0000

Data Index: 1231328 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1220. Min Act: -0.0000

Data Index: 611256 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.2061. Min Range: -0.2061

Max Act: 0.1220. Min Act: -0.0000

Data Index: 858662 (C4 (Web Text))

Max Activating Token Index: 723