Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3648 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.2031. Min Act: -0.0001

Data Index: 1094844 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1898. Min Act: -0.0002

Data Index: 1020250 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.2010. Min Act: -0.0002

Data Index: 118702 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1924. Min Act: -0.0001

Data Index: 348582 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1685. Min Act: -0.0001

Data Index: 857634 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1650. Min Act: -0.0001

Data Index: 951996 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1524. Min Act: -0.0002

Data Index: 628789 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1591. Min Act: -0.0002

Data Index: 1343707 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1511. Min Act: -0.0002

Data Index: 856901 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1452. Min Act: -0.0002

Data Index: 435546 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1453. Min Act: -0.0002

Data Index: 808837 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1322. Min Act: -0.0002

Data Index: 209052 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1468. Min Act: -0.0002

Data Index: 267447 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1522. Min Act: -0.0001

Data Index: 1137688 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1460. Min Act: -0.0001

Data Index: 660134 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1405. Min Act: -0.0002

Data Index: 382125 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1356. Min Act: -0.0002

Data Index: 755916 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1345. Min Act: -0.0001

Data Index: 928373 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1418. Min Act: -0.0002

Data Index: 212567 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1421. Min Act: -0.0002

Data Index: 523761 (C4 (Web Text))

Max Activating Token Index: 31