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

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

Neuron 3533 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1698. Min Act: -0.0002

Data Index: 443567 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1595. Min Act: -0.0002

Data Index: 1114686 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1456. Min Act: -0.0002

Data Index: 249638 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1435. Min Act: -0.0002

Data Index: 1276574 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1431. Min Act: -0.0002

Data Index: 1174513 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1419. Min Act: -0.0002

Data Index: 1292858 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1415. Min Act: -0.0002

Data Index: 382595 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1380. Min Act: -0.0002

Data Index: 473496 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1372. Min Act: -0.0002

Data Index: 881466 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1360. Min Act: -0.0002

Data Index: 374992 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1314. Min Act: -0.0002

Data Index: 811792 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1287. Min Act: -0.0002

Data Index: 1345393 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1283. Min Act: -0.0002

Data Index: 1014827 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1277. Min Act: -0.0002

Data Index: 270219 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1273. Min Act: -0.0002

Data Index: 211928 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1269. Min Act: -0.0002

Data Index: 1258011 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1268. Min Act: -0.0002

Data Index: 395349 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1264. Min Act: -0.0002

Data Index: 289682 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1263. Min Act: -0.0002

Data Index: 1268338 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1261. Min Act: -0.0002

Data Index: 1112045 (C4 (Web Text))

Max Activating Token Index: 898