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

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

Neuron 128 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: 0.1793. Min Range: -0.1793

Max Act: 0.1793. Min Act: -0.0002

Data Index: 61346 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1696. Min Act: -0.0002

Data Index: 191837 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1565. Min Act: -0.0002

Data Index: 1213586 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1573. Min Act: -0.0002

Data Index: 386141 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1518. Min Act: -0.0002

Data Index: 843631 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1456. Min Act: -0.0002

Data Index: 483111 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1437. Min Act: -0.0002

Data Index: 674439 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1485. Min Act: -0.0002

Data Index: 407286 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1403. Min Act: -0.0002

Data Index: 227345 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1389. Min Act: -0.0002

Data Index: 673272 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1430. Min Act: -0.0002

Data Index: 926166 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1373. Min Act: -0.0002

Data Index: 854828 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1415. Min Act: -0.0002

Data Index: 1021707 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1334. Min Act: -0.0002

Data Index: 69154 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1276. Min Act: -0.0002

Data Index: 471750 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1331. Min Act: -0.0002

Data Index: 565655 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1290. Min Act: -0.0002

Data Index: 1278095 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1351. Min Act: -0.0002

Data Index: 585047 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1340. Min Act: -0.0002

Data Index: 1210516 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1323. Min Act: -0.0002

Data Index: 1077106 (C4 (Web Text))

Max Activating Token Index: 136