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

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

Neuron 3451 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5177. Min Range: -1.5177

Max Act: 1.5177. Min Act: -0.0001

Data Index: 134821 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 1.5177. Min Range: -1.5177

Max Act: 1.3044. Min Act: -0.0001

Data Index: 927636 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 1.5177. Min Range: -1.5177

Max Act: 1.3413. Min Act: -0.0001

Data Index: 867315 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 1.5177. Min Range: -1.5177

Max Act: 1.3378. Min Act: -0.0001

Data Index: 648635 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 1.5177. Min Range: -1.5177

Max Act: 1.2658. Min Act: -0.0001

Data Index: 1161478 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 1.5177. Min Range: -1.5177

Max Act: 1.2632. Min Act: -0.0001

Data Index: 1222452 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 1.5177. Min Range: -1.5177

Max Act: 1.2176. Min Act: -0.0001

Data Index: 875959 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 1.5177. Min Range: -1.5177

Max Act: 1.3040. Min Act: -0.0001

Data Index: 106548 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 1.5177. Min Range: -1.5177

Max Act: 1.2971. Min Act: -0.0001

Data Index: 844263 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 1.5177. Min Range: -1.5177

Max Act: 1.2773. Min Act: -0.0001

Data Index: 965752 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 1.5177. Min Range: -1.5177

Max Act: 1.1718. Min Act: -0.0001

Data Index: 1162203 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 1.5177. Min Range: -1.5177

Max Act: 1.2230. Min Act: -0.0001

Data Index: 1340749 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 1.5177. Min Range: -1.5177

Max Act: 1.2399. Min Act: -0.0001

Data Index: 538769 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 1.5177. Min Range: -1.5177

Max Act: 1.1281. Min Act: -0.0001

Data Index: 279310 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 1.5177. Min Range: -1.5177

Max Act: 1.0917. Min Act: -0.0001

Data Index: 1143759 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 1.5177. Min Range: -1.5177

Max Act: 1.1838. Min Act: -0.0001

Data Index: 1313359 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 1.5177. Min Range: -1.5177

Max Act: 1.1751. Min Act: -0.0001

Data Index: 28434 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 1.5177. Min Range: -1.5177

Max Act: 1.1301. Min Act: -0.0001

Data Index: 1035730 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 1.5177. Min Range: -1.5177

Max Act: 1.0986. Min Act: -0.0001

Data Index: 373885 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 1.5177. Min Range: -1.5177

Max Act: 1.0291. Min Act: -0.0001

Data Index: 590801 (C4 (Web Text))

Max Activating Token Index: 801