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

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

Neuron 3631 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8147. Min Range: -1.8147

Max Act: 1.8147. Min Act: -0.0001

Data Index: 673586 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 1.8147. Min Range: -1.8147

Max Act: 1.5801. Min Act: -0.0001

Data Index: 730056 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 1.8147. Min Range: -1.8147

Max Act: 1.2568. Min Act: -0.0001

Data Index: 1067523 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 1.8147. Min Range: -1.8147

Max Act: 1.4688. Min Act: -0.0001

Data Index: 141573 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 1.8147. Min Range: -1.8147

Max Act: 1.2944. Min Act: -0.0001

Data Index: 153527 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 1.8147. Min Range: -1.8147

Max Act: 1.0196. Min Act: -0.0001

Data Index: 1035411 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 1.8147. Min Range: -1.8147

Max Act: 1.1340. Min Act: -0.0001

Data Index: 1348732 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 1.8147. Min Range: -1.8147

Max Act: 1.4027. Min Act: -0.0001

Data Index: 792018 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 1.8147. Min Range: -1.8147

Max Act: 1.1860. Min Act: -0.0001

Data Index: 607283 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 1.8147. Min Range: -1.8147

Max Act: 1.2866. Min Act: -0.0001

Data Index: 821459 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 1.8147. Min Range: -1.8147

Max Act: 1.2391. Min Act: -0.0001

Data Index: 1277299 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 1.8147. Min Range: -1.8147

Max Act: 1.4214. Min Act: -0.0001

Data Index: 208133 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 1.8147. Min Range: -1.8147

Max Act: 1.2318. Min Act: -0.0001

Data Index: 117988 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 1.8147. Min Range: -1.8147

Max Act: 1.2139. Min Act: -0.0001

Data Index: 1168233 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 1.8147. Min Range: -1.8147

Max Act: 1.1226. Min Act: -0.0001

Data Index: 807770 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 1.8147. Min Range: -1.8147

Max Act: 1.1587. Min Act: -0.0001

Data Index: 31627 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 1.8147. Min Range: -1.8147

Max Act: 1.1345. Min Act: -0.0001

Data Index: 500202 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 1.8147. Min Range: -1.8147

Max Act: 1.1684. Min Act: -0.0001

Data Index: 175378 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 1.8147. Min Range: -1.8147

Max Act: 1.2573. Min Act: -0.0001

Data Index: 1246032 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 1.8147. Min Range: -1.8147

Max Act: 1.2543. Min Act: -0.0001

Data Index: 896372 (C4 (Web Text))

Max Activating Token Index: 10