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

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

Neuron 64 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1097322 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2906. Min Act: -0.0000

Data Index: 928590 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2679. Min Act: -0.0001

Data Index: 767500 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2743. Min Act: -0.0000

Data Index: 1115879 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2736. Min Act: -0.0001

Data Index: 357073 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2621. Min Act: -0.0001

Data Index: 1310638 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2566. Min Act: -0.0001

Data Index: 496783 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2566. Min Act: -0.0000

Data Index: 1219160 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2534. Min Act: -0.0001

Data Index: 1302738 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2368. Min Act: -0.0000

Data Index: 142961 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2353. Min Act: -0.0000

Data Index: 1062474 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2447. Min Act: -0.0000

Data Index: 445031 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2351. Min Act: -0.0000

Data Index: 760080 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2442. Min Act: -0.0000

Data Index: 116642 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2238. Min Act: -0.0001

Data Index: 258167 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2586. Min Act: -0.0000

Data Index: 1304631 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2364. Min Act: -0.0000

Data Index: 307662 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2432. Min Act: -0.0001

Data Index: 72948 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2484. Min Act: -0.0000

Data Index: 1356836 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2286. Min Act: -0.0000

Data Index: 444489 (C4 (Web Text))

Max Activating Token Index: 692