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

Dataset: The Pile

Neuron 26 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1358. Min Range: -1.1358

Max Act: 1.1203. Min Act: -0.0000

Data Index: 358969 (The Pile)

Max Activating Token Index: 549

Text #1

Max Range: 1.1358. Min Range: -1.1358

Max Act: 1.0716. Min Act: -0.0000

Data Index: 914403 (The Pile)

Max Activating Token Index: 220

Text #2

Max Range: 1.1358. Min Range: -1.1358

Max Act: 1.1331. Min Act: -0.0000

Data Index: 1773299 (The Pile)

Max Activating Token Index: 737

Text #3

Max Range: 1.1358. Min Range: -1.1358

Max Act: 1.0541. Min Act: -0.0000

Data Index: 1915533 (The Pile)

Max Activating Token Index: 915

Text #4

Max Range: 1.1358. Min Range: -1.1358

Max Act: 1.1358. Min Act: -0.0000

Data Index: 533535 (The Pile)

Max Activating Token Index: 311

Text #5

Max Range: 1.1358. Min Range: -1.1358

Max Act: 1.0667. Min Act: -0.0000

Data Index: 1157719 (The Pile)

Max Activating Token Index: 497

Text #6

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.8956. Min Act: -0.0000

Data Index: 1028237 (The Pile)

Max Activating Token Index: 193

Text #7

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.9637. Min Act: -0.0000

Data Index: 158444 (The Pile)

Max Activating Token Index: 412

Text #8

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.9602. Min Act: -0.0000

Data Index: 1193044 (The Pile)

Max Activating Token Index: 447

Text #9

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.8624. Min Act: -0.0000

Data Index: 326780 (The Pile)

Max Activating Token Index: 862

Text #10

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.9340. Min Act: -0.0000

Data Index: 710334 (The Pile)

Max Activating Token Index: 514

Text #11

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.8790. Min Act: -0.0000

Data Index: 240624 (The Pile)

Max Activating Token Index: 710

Text #12

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.8468. Min Act: -0.0000

Data Index: 725220 (The Pile)

Max Activating Token Index: 770

Text #13

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.8049. Min Act: -0.0000

Data Index: 566178 (The Pile)

Max Activating Token Index: 834

Text #14

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.8227. Min Act: -0.0000

Data Index: 1670052 (The Pile)

Max Activating Token Index: 228

Text #15

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.8751. Min Act: -0.0000

Data Index: 1360458 (The Pile)

Max Activating Token Index: 292

Text #16

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.9580. Min Act: -0.0000

Data Index: 221180 (The Pile)

Max Activating Token Index: 296

Text #17

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.8713. Min Act: -0.0000

Data Index: 1779110 (The Pile)

Max Activating Token Index: 317

Text #18

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.9125. Min Act: -0.0000

Data Index: 661915 (The Pile)

Max Activating Token Index: 202

Text #19

Max Range: 1.1358. Min Range: -1.1358

Max Act: 0.9432. Min Act: -0.0000

Data Index: 785108 (The Pile)

Max Activating Token Index: 454