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

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

Neuron 4041 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1541. Min Range: -1.1541

Max Act: 1.1541. Min Act: 0.0001

Data Index: 990296 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.9328. Min Act: 0.0001

Data Index: 1187492 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.8436. Min Act: 0.0001

Data Index: 1149150 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.7244. Min Act: -0.0000

Data Index: 895106 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.7232. Min Act: 0.0000

Data Index: 534465 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.6950. Min Act: -0.0000

Data Index: 811405 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.6760. Min Act: 0.0001

Data Index: 570692 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.6727. Min Act: -0.0000

Data Index: 965327 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.6962. Min Act: 0.0001

Data Index: 658451 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.6957. Min Act: 0.0001

Data Index: 476374 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.6693. Min Act: 0.0000

Data Index: 894862 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.6586. Min Act: -0.0000

Data Index: 965579 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.6580. Min Act: 0.0002

Data Index: 1154979 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.6279. Min Act: 0.0000

Data Index: 784075 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.6425. Min Act: -0.0000

Data Index: 366428 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.6234. Min Act: -0.0000

Data Index: 940497 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.6350. Min Act: -0.0000

Data Index: 30380 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.5942. Min Act: -0.0000

Data Index: 616732 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.6109. Min Act: -0.0000

Data Index: 453581 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 1.1541. Min Range: -1.1541

Max Act: 0.6222. Min Act: -0.0000

Data Index: 369091 (C4 (Web Text))

Max Activating Token Index: 727