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

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

Neuron 1433 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2395. Min Act: -0.0000

Data Index: 902620 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2152. Min Act: -0.0000

Data Index: 328532 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1652. Min Act: -0.0000

Data Index: 293190 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1665. Min Act: -0.0001

Data Index: 1120599 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1699. Min Act: -0.0000

Data Index: 29174 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1835. Min Act: -0.0000

Data Index: 1254349 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1619. Min Act: -0.0000

Data Index: 484563 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1677. Min Act: -0.0000

Data Index: 866047 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1676. Min Act: -0.0000

Data Index: 424751 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1666. Min Act: -0.0001

Data Index: 25055 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1640. Min Act: -0.0000

Data Index: 214063 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1697. Min Act: -0.0000

Data Index: 188776 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1420. Min Act: -0.0000

Data Index: 1164965 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1634. Min Act: -0.0000

Data Index: 885404 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1486. Min Act: -0.0000

Data Index: 376809 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1601. Min Act: -0.0000

Data Index: 674609 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1541. Min Act: -0.0000

Data Index: 367472 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1626. Min Act: -0.0000

Data Index: 783625 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1704. Min Act: -0.0000

Data Index: 480012 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1489. Min Act: -0.0000

Data Index: 1076301 (C4 (Web Text))

Max Activating Token Index: 855