Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4698 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.8222. Min Act: -0.0000

Data Index: 107451 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.7756. Min Act: -0.0000

Data Index: 484192 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6779. Min Act: -0.0000

Data Index: 367315 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.7452. Min Act: -0.0000

Data Index: 1018658 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6725. Min Act: -0.0000

Data Index: 151077 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6656. Min Act: -0.0000

Data Index: 572870 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.7198. Min Act: -0.0000

Data Index: 495369 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6246. Min Act: -0.0000

Data Index: 736602 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6080. Min Act: -0.0000

Data Index: 151763 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6482. Min Act: -0.0000

Data Index: 1199369 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6380. Min Act: -0.0000

Data Index: 238494 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6307. Min Act: -0.0000

Data Index: 74493 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6499. Min Act: -0.0000

Data Index: 488627 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.5773. Min Act: -0.0000

Data Index: 859231 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1263791 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.4675. Min Act: -0.0000

Data Index: 148003 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.4591. Min Act: -0.0000

Data Index: 760974 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.4453. Min Act: -0.0000

Data Index: 318191 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.5067. Min Act: -0.0000

Data Index: 395703 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.4678. Min Act: -0.0000

Data Index: 768656 (C4 (Web Text))

Max Activating Token Index: 750