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

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

Neuron 3908 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: 1.0914. Min Range: -1.0914

Max Act: 1.0914. Min Act: -0.0001

Data Index: 767185 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 1.0914. Min Range: -1.0914

Max Act: 1.0406. Min Act: -0.0001

Data Index: 761313 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.9443. Min Act: -0.0001

Data Index: 700253 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.9528. Min Act: -0.0001

Data Index: 1350926 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.9203. Min Act: -0.0001

Data Index: 154941 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.8434. Min Act: -0.0001

Data Index: 852575 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.8611. Min Act: -0.0001

Data Index: 881244 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.8447. Min Act: -0.0001

Data Index: 1146868 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.8475. Min Act: -0.0001

Data Index: 797216 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.8551. Min Act: -0.0001

Data Index: 699385 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.8156. Min Act: -0.0001

Data Index: 894128 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.8750. Min Act: -0.0001

Data Index: 862448 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.8227. Min Act: -0.0001

Data Index: 714467 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.8483. Min Act: -0.0001

Data Index: 723671 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.8415. Min Act: -0.0001

Data Index: 518075 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.8464. Min Act: -0.0001

Data Index: 943635 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.8170. Min Act: -0.0001

Data Index: 802648 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.8100. Min Act: -0.0001

Data Index: 874938 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.8069. Min Act: -0.0001

Data Index: 753931 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 1.0914. Min Range: -1.0914

Max Act: 0.8304. Min Act: -0.0001

Data Index: 122538 (C4 (Web Text))

Max Activating Token Index: 573