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

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

Neuron 276 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.8388. Min Act: -0.0002

Data Index: 36226 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.9452. Min Act: -0.0001

Data Index: 204893 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 1.1208. Min Range: -1.1208

Max Act: 1.1208. Min Act: -0.0001

Data Index: 229995 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.8863. Min Act: -0.0001

Data Index: 162143 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 1.1208. Min Range: -1.1208

Max Act: 1.0586. Min Act: -0.0002

Data Index: 828526 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.9807. Min Act: -0.0002

Data Index: 330884 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.9232. Min Act: -0.0001

Data Index: 121205 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 1.1208. Min Range: -1.1208

Max Act: 1.0274. Min Act: -0.0001

Data Index: 763401 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.9982. Min Act: -0.0001

Data Index: 1001012 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.8981. Min Act: -0.0002

Data Index: 566292 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 1.1208. Min Range: -1.1208

Max Act: 1.0556. Min Act: -0.0002

Data Index: 171364 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.8971. Min Act: -0.0001

Data Index: 994424 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.8468. Min Act: -0.0001

Data Index: 1014096 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.8354. Min Act: -0.0002

Data Index: 1136143 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.7634. Min Act: -0.0001

Data Index: 1244791 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.9047. Min Act: -0.0002

Data Index: 873597 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.7532. Min Act: -0.0001

Data Index: 189619 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.8434. Min Act: -0.0001

Data Index: 684227 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.9678. Min Act: -0.0001

Data Index: 1169271 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 1.1208. Min Range: -1.1208

Max Act: 0.8176. Min Act: -0.0001

Data Index: 1256685 (C4 (Web Text))

Max Activating Token Index: 703