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

Dataset: The Pile

Neuron 4747 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.3214. Min Act: -0.0000

Data Index: 621392 (The Pile)

Max Activating Token Index: 328

Text #1

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1449488 (The Pile)

Max Activating Token Index: 434

Text #2

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2719. Min Act: -0.0000

Data Index: 743796 (The Pile)

Max Activating Token Index: 74

Text #3

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2762. Min Act: -0.0000

Data Index: 1754732 (The Pile)

Max Activating Token Index: 531

Text #4

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2482. Min Act: -0.0000

Data Index: 670975 (The Pile)

Max Activating Token Index: 472

Text #5

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2463. Min Act: -0.0000

Data Index: 1111358 (The Pile)

Max Activating Token Index: 925

Text #6

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1100342 (The Pile)

Max Activating Token Index: 407

Text #7

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2564. Min Act: -0.0000

Data Index: 265503 (The Pile)

Max Activating Token Index: 686

Text #8

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2606. Min Act: -0.0000

Data Index: 961300 (The Pile)

Max Activating Token Index: 753

Text #9

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2527. Min Act: -0.0000

Data Index: 782491 (The Pile)

Max Activating Token Index: 766

Text #10

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2479. Min Act: -0.0000

Data Index: 1748647 (The Pile)

Max Activating Token Index: 383

Text #11

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2437. Min Act: -0.0000

Data Index: 1358263 (The Pile)

Max Activating Token Index: 1022

Text #12

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2316. Min Act: -0.0000

Data Index: 1227336 (The Pile)

Max Activating Token Index: 665

Text #13

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2339. Min Act: -0.0000

Data Index: 441901 (The Pile)

Max Activating Token Index: 552

Text #14

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2266. Min Act: -0.0000

Data Index: 489733 (The Pile)

Max Activating Token Index: 583

Text #15

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1310155 (The Pile)

Max Activating Token Index: 803

Text #16

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2910. Min Act: -0.0000

Data Index: 949771 (The Pile)

Max Activating Token Index: 605

Text #17

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2628. Min Act: -0.0000

Data Index: 1159784 (The Pile)

Max Activating Token Index: 990

Text #18

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2288. Min Act: -0.0000

Data Index: 526330 (The Pile)

Max Activating Token Index: 100

Text #19

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2341. Min Act: -0.0000

Data Index: 912728 (The Pile)

Max Activating Token Index: 201