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

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

Neuron 825 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: 0.7745. Min Range: -0.7745

Max Act: 0.7745. Min Act: -0.0001

Data Index: 1176276 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.7726. Min Act: -0.0001

Data Index: 975706 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.7295. Min Act: -0.0001

Data Index: 1285143 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.7210. Min Act: -0.0001

Data Index: 793475 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.7191. Min Act: -0.0001

Data Index: 1011913 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.7103. Min Act: -0.0001

Data Index: 1277511 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6768. Min Act: -0.0001

Data Index: 323069 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6976. Min Act: -0.0001

Data Index: 828163 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6700. Min Act: -0.0001

Data Index: 317511 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6946. Min Act: -0.0001

Data Index: 860716 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.7095. Min Act: -0.0001

Data Index: 268297 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.7317. Min Act: -0.0001

Data Index: 1233809 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.7194. Min Act: -0.0001

Data Index: 395531 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6944. Min Act: -0.0001

Data Index: 997426 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6886. Min Act: -0.0001

Data Index: 742612 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6453. Min Act: -0.0001

Data Index: 639586 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6848. Min Act: -0.0001

Data Index: 128085 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6201. Min Act: -0.0001

Data Index: 443108 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.7015. Min Act: -0.0001

Data Index: 359914 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6513. Min Act: -0.0001

Data Index: 472929 (C4 (Web Text))

Max Activating Token Index: 819