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

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

Neuron 412 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4173. Min Range: -1.4173

Max Act: 1.4173. Min Act: -0.0001

Data Index: 800089 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 1.4173. Min Range: -1.4173

Max Act: 1.3798. Min Act: -0.0000

Data Index: 316685 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 1.4173. Min Range: -1.4173

Max Act: 1.2383. Min Act: -0.0001

Data Index: 362324 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 1.4173. Min Range: -1.4173

Max Act: 1.2142. Min Act: -0.0000

Data Index: 814757 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 1.4173. Min Range: -1.4173

Max Act: 1.1748. Min Act: -0.0000

Data Index: 51392 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 1.4173. Min Range: -1.4173

Max Act: 1.1027. Min Act: -0.0001

Data Index: 434150 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 1.4173. Min Range: -1.4173

Max Act: 1.0294. Min Act: -0.0001

Data Index: 1312931 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 1.4173. Min Range: -1.4173

Max Act: 0.9429. Min Act: -0.0000

Data Index: 650089 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 1.4173. Min Range: -1.4173

Max Act: 1.0310. Min Act: -0.0000

Data Index: 579579 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 1.4173. Min Range: -1.4173

Max Act: 1.0675. Min Act: -0.0001

Data Index: 527034 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 1.4173. Min Range: -1.4173

Max Act: 0.9017. Min Act: -0.0001

Data Index: 95682 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 1.4173. Min Range: -1.4173

Max Act: 0.8879. Min Act: -0.0001

Data Index: 458782 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 1.4173. Min Range: -1.4173

Max Act: 0.8167. Min Act: -0.0001

Data Index: 785611 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 1.4173. Min Range: -1.4173

Max Act: 0.8381. Min Act: -0.0001

Data Index: 170837 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 1.4173. Min Range: -1.4173

Max Act: 0.8177. Min Act: -0.0000

Data Index: 1142888 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 1.4173. Min Range: -1.4173

Max Act: 0.8213. Min Act: -0.0000

Data Index: 601129 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 1.4173. Min Range: -1.4173

Max Act: 0.8144. Min Act: -0.0001

Data Index: 284493 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 1.4173. Min Range: -1.4173

Max Act: 0.8166. Min Act: -0.0001

Data Index: 1301408 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 1.4173. Min Range: -1.4173

Max Act: 0.8272. Min Act: -0.0000

Data Index: 768093 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 1.4173. Min Range: -1.4173

Max Act: 0.8214. Min Act: -0.0000

Data Index: 374227 (C4 (Web Text))

Max Activating Token Index: 978