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

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

Neuron 3940 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: 1.2199. Min Range: -1.2199

Max Act: 1.2199. Min Act: -0.0001

Data Index: 931144 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 1.2199. Min Range: -1.2199

Max Act: 1.1902. Min Act: -0.0001

Data Index: 514304 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 1.2199. Min Range: -1.2199

Max Act: 1.1511. Min Act: -0.0001

Data Index: 132449 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 1.2199. Min Range: -1.2199

Max Act: 1.1176. Min Act: -0.0001

Data Index: 921478 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 1.2199. Min Range: -1.2199

Max Act: 1.0834. Min Act: -0.0001

Data Index: 1129814 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 1.2199. Min Range: -1.2199

Max Act: 1.1401. Min Act: -0.0001

Data Index: 654285 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 1.2199. Min Range: -1.2199

Max Act: 1.0967. Min Act: -0.0001

Data Index: 627028 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 1.2199. Min Range: -1.2199

Max Act: 1.1106. Min Act: -0.0001

Data Index: 1088080 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 1.2199. Min Range: -1.2199

Max Act: 1.0825. Min Act: -0.0001

Data Index: 813739 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 1.2199. Min Range: -1.2199

Max Act: 1.1439. Min Act: -0.0001

Data Index: 779213 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 1.2199. Min Range: -1.2199

Max Act: 1.1199. Min Act: -0.0001

Data Index: 1138687 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 1.2199. Min Range: -1.2199

Max Act: 1.0467. Min Act: -0.0001

Data Index: 32887 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 1.2199. Min Range: -1.2199

Max Act: 1.0189. Min Act: -0.0001

Data Index: 264871 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 1.2199. Min Range: -1.2199

Max Act: 0.9857. Min Act: -0.0001

Data Index: 336232 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 1.2199. Min Range: -1.2199

Max Act: 1.0014. Min Act: -0.0001

Data Index: 586865 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 1.2199. Min Range: -1.2199

Max Act: 1.0861. Min Act: -0.0001

Data Index: 169013 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 1.2199. Min Range: -1.2199

Max Act: 0.9605. Min Act: -0.0001

Data Index: 1231140 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 1.2199. Min Range: -1.2199

Max Act: 1.0397. Min Act: -0.0001

Data Index: 274357 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 1.2199. Min Range: -1.2199

Max Act: 1.0447. Min Act: -0.0001

Data Index: 811729 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 1.2199. Min Range: -1.2199

Max Act: 0.9441. Min Act: -0.0001

Data Index: 1293059 (C4 (Web Text))

Max Activating Token Index: 946