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

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

Neuron 10 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9248. Min Range: -4.9248

Max Act: 4.9248. Min Act: -0.0000

Data Index: 795116 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 4.9248. Min Range: -4.9248

Max Act: 4.1371. Min Act: -0.0000

Data Index: 638726 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 4.9248. Min Range: -4.9248

Max Act: 3.3143. Min Act: -0.0000

Data Index: 274019 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 4.9248. Min Range: -4.9248

Max Act: 2.9659. Min Act: -0.0000

Data Index: 461257 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 4.9248. Min Range: -4.9248

Max Act: 2.7456. Min Act: -0.0000

Data Index: 1206692 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 4.9248. Min Range: -4.9248

Max Act: 2.4566. Min Act: -0.0000

Data Index: 252247 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 4.9248. Min Range: -4.9248

Max Act: 2.2214. Min Act: -0.0000

Data Index: 218315 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 4.9248. Min Range: -4.9248

Max Act: 2.1993. Min Act: -0.0000

Data Index: 664831 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 4.9248. Min Range: -4.9248

Max Act: 2.0353. Min Act: -0.0000

Data Index: 459863 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 4.9248. Min Range: -4.9248

Max Act: 2.0140. Min Act: -0.0000

Data Index: 952834 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 4.9248. Min Range: -4.9248

Max Act: 1.9668. Min Act: -0.0000

Data Index: 922599 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 4.9248. Min Range: -4.9248

Max Act: 1.9257. Min Act: -0.0000

Data Index: 565124 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 4.9248. Min Range: -4.9248

Max Act: 1.9358. Min Act: -0.0000

Data Index: 550885 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 4.9248. Min Range: -4.9248

Max Act: 1.8811. Min Act: -0.0000

Data Index: 1014223 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 4.9248. Min Range: -4.9248

Max Act: 1.7965. Min Act: -0.0000

Data Index: 1043995 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 4.9248. Min Range: -4.9248

Max Act: 1.7820. Min Act: -0.0000

Data Index: 86006 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 4.9248. Min Range: -4.9248

Max Act: 1.9714. Min Act: -0.0000

Data Index: 732936 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 4.9248. Min Range: -4.9248

Max Act: 2.1373. Min Act: -0.0000

Data Index: 474607 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 4.9248. Min Range: -4.9248

Max Act: 1.8352. Min Act: -0.0000

Data Index: 1207645 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 4.9248. Min Range: -4.9248

Max Act: 1.8617. Min Act: -0.0000

Data Index: 771918 (C4 (Web Text))

Max Activating Token Index: 267