Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 485 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2638. Min Act: -0.0002

Data Index: 580242 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1989. Min Act: -0.0003

Data Index: 606465 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1973. Min Act: -0.0003

Data Index: 74791 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1722. Min Act: -0.0002

Data Index: 1166698 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1430. Min Act: -0.0003

Data Index: 1260954 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1442. Min Act: -0.0002

Data Index: 396702 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1525. Min Act: -0.0003

Data Index: 190961 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1596. Min Act: -0.0003

Data Index: 186130 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1422. Min Act: -0.0003

Data Index: 635482 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1494. Min Act: -0.0003

Data Index: 1023527 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1459. Min Act: -0.0003

Data Index: 890632 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1505. Min Act: -0.0003

Data Index: 693015 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1429. Min Act: -0.0003

Data Index: 1145316 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1381. Min Act: -0.0003

Data Index: 326008 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1351. Min Act: -0.0003

Data Index: 814967 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1357. Min Act: -0.0003

Data Index: 1208619 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1348. Min Act: -0.0003

Data Index: 432112 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1311. Min Act: -0.0003

Data Index: 1062791 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1338. Min Act: -0.0003

Data Index: 947132 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1334. Min Act: -0.0003

Data Index: 1546395 (Python Code)

Max Activating Token Index: 983