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

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

Neuron 5226 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3066. Min Range: -2.3066

Max Act: 2.3066. Min Act: -0.0000

Data Index: 938638 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 2.3066. Min Range: -2.3066

Max Act: 2.0694. Min Act: -0.0000

Data Index: 346461 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 2.3066. Min Range: -2.3066

Max Act: 1.8534. Min Act: -0.0000

Data Index: 990793 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 2.3066. Min Range: -2.3066

Max Act: 1.7377. Min Act: -0.0000

Data Index: 1076892 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 2.3066. Min Range: -2.3066

Max Act: 1.7418. Min Act: -0.0000

Data Index: 941095 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 2.3066. Min Range: -2.3066

Max Act: 1.5187. Min Act: -0.0000

Data Index: 1176519 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 2.3066. Min Range: -2.3066

Max Act: 1.5750. Min Act: -0.0000

Data Index: 359299 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 2.3066. Min Range: -2.3066

Max Act: 1.6377. Min Act: -0.0000

Data Index: 1235197 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 2.3066. Min Range: -2.3066

Max Act: 1.6358. Min Act: -0.0000

Data Index: 934976 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 2.3066. Min Range: -2.3066

Max Act: 1.6311. Min Act: -0.0000

Data Index: 1323929 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 2.3066. Min Range: -2.3066

Max Act: 1.5169. Min Act: -0.0000

Data Index: 1303057 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 2.3066. Min Range: -2.3066

Max Act: 1.5156. Min Act: 0.0000

Data Index: 604606 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 2.3066. Min Range: -2.3066

Max Act: 1.4973. Min Act: -0.0000

Data Index: 1111423 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 2.3066. Min Range: -2.3066

Max Act: 1.4677. Min Act: -0.0000

Data Index: 480569 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 2.3066. Min Range: -2.3066

Max Act: 1.4613. Min Act: -0.0000

Data Index: 1052222 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 2.3066. Min Range: -2.3066

Max Act: 1.3574. Min Act: -0.0000

Data Index: 1233473 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 2.3066. Min Range: -2.3066

Max Act: 1.4109. Min Act: -0.0000

Data Index: 177955 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 2.3066. Min Range: -2.3066

Max Act: 1.3891. Min Act: -0.0000

Data Index: 1202749 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 2.3066. Min Range: -2.3066

Max Act: 1.4588. Min Act: -0.0000

Data Index: 320286 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 2.3066. Min Range: -2.3066

Max Act: 1.3514. Min Act: -0.0000

Data Index: 889140 (C4 (Web Text))

Max Activating Token Index: 818