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

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

Neuron 312 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.8149. Min Act: -0.0000

Data Index: 85265 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1553916 (Python Code)

Max Activating Token Index: 186

Text #2

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.6111. Min Act: -0.0000

Data Index: 917620 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.5790. Min Act: -0.0000

Data Index: 522366 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1257421 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.5622. Min Act: -0.0000

Data Index: 20294 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.5578. Min Act: -0.0000

Data Index: 826628 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.5111. Min Act: -0.0000

Data Index: 442360 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.5264. Min Act: -0.0000

Data Index: 1593282 (Python Code)

Max Activating Token Index: 644

Text #9

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.4959. Min Act: -0.0000

Data Index: 1477475 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.4906. Min Act: -0.0000

Data Index: 553743 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.4701. Min Act: -0.0000

Data Index: 49044 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.4658. Min Act: -0.0000

Data Index: 566141 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.4642. Min Act: -0.0000

Data Index: 1184651 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.5056. Min Act: -0.0000

Data Index: 1273286 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.4716. Min Act: -0.0000

Data Index: 1297612 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.4334. Min Act: -0.0000

Data Index: 182609 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.4606. Min Act: -0.0000

Data Index: 1189775 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.4502. Min Act: -0.0000

Data Index: 816699 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 0.8149. Min Range: -0.8149

Max Act: 0.4461. Min Act: -0.0000

Data Index: 912968 (C4 (Web Text))

Max Activating Token Index: 806