Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3676 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1428570 (Python Code)

Max Activating Token Index: 840

Text #1

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1384283 (Python Code)

Max Activating Token Index: 886

Text #2

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0306. Min Act: -0.0002

Data Index: 1473922 (Python Code)

Max Activating Token Index: 537

Text #3

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1579411 (Python Code)

Max Activating Token Index: 918

Text #4

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0262. Min Act: -0.0002

Data Index: 809633 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0243. Min Act: -0.0002

Data Index: 1459633 (Python Code)

Max Activating Token Index: 199

Text #6

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1499159 (Python Code)

Max Activating Token Index: 960

Text #7

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0243. Min Act: -0.0002

Data Index: 145200 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0221. Min Act: -0.0002

Data Index: 1542142 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0169. Min Act: -0.0002

Data Index: 333403 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0215. Min Act: -0.0002

Data Index: 71012 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1445535 (Python Code)

Max Activating Token Index: 880

Text #12

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0214. Min Act: -0.0002

Data Index: 1243500 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0243. Min Act: -0.0002

Data Index: 515048 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0224. Min Act: -0.0002

Data Index: 253459 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0214. Min Act: -0.0002

Data Index: 303582 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1064093 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1030621 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0201. Min Act: -0.0003

Data Index: 54199 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0197. Min Act: -0.0002

Data Index: 167528 (C4 (Web Text))

Max Activating Token Index: 784