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

Dataset: The Pile

Neuron 2190 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.2351. Min Act: -0.0000

Data Index: 175208 (The Pile)

Max Activating Token Index: 1005

Text #1

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.2264. Min Act: -0.0000

Data Index: 1486614 (The Pile)

Max Activating Token Index: 776

Text #2

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.1516. Min Act: -0.0000

Data Index: 1544648 (The Pile)

Max Activating Token Index: 793

Text #3

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.1967. Min Act: -0.0000

Data Index: 1566927 (The Pile)

Max Activating Token Index: 472

Text #4

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.1658. Min Act: -0.0000

Data Index: 948050 (The Pile)

Max Activating Token Index: 470

Text #5

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.2226. Min Act: -0.0000

Data Index: 1774837 (The Pile)

Max Activating Token Index: 664

Text #6

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.1552. Min Act: -0.0000

Data Index: 738751 (The Pile)

Max Activating Token Index: 332

Text #7

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.1458. Min Act: -0.0000

Data Index: 904260 (The Pile)

Max Activating Token Index: 498

Text #8

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.1428. Min Act: -0.0000

Data Index: 1980905 (The Pile)

Max Activating Token Index: 289

Text #9

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.0750. Min Act: -0.0000

Data Index: 451577 (The Pile)

Max Activating Token Index: 450

Text #10

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.1359. Min Act: -0.0000

Data Index: 1138626 (The Pile)

Max Activating Token Index: 642

Text #11

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.1362. Min Act: -0.0000

Data Index: 349982 (The Pile)

Max Activating Token Index: 515

Text #12

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.0553. Min Act: -0.0000

Data Index: 178691 (The Pile)

Max Activating Token Index: 661

Text #13

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.1953. Min Act: -0.0000

Data Index: 1744599 (The Pile)

Max Activating Token Index: 520

Text #14

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.1275. Min Act: -0.0000

Data Index: 296219 (The Pile)

Max Activating Token Index: 615

Text #15

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.0391. Min Act: -0.0000

Data Index: 1866657 (The Pile)

Max Activating Token Index: 654

Text #16

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.0367. Min Act: -0.0000

Data Index: 1575609 (The Pile)

Max Activating Token Index: 577

Text #17

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.1041. Min Act: -0.0000

Data Index: 1702209 (The Pile)

Max Activating Token Index: 647

Text #18

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.0924. Min Act: -0.0000

Data Index: 1891191 (The Pile)

Max Activating Token Index: 887

Text #19

Max Range: 1.2351. Min Range: -1.2351

Max Act: 1.0140. Min Act: -0.0000

Data Index: 266206 (The Pile)

Max Activating Token Index: 479