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

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

Neuron 4173 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: 0.6426. Min Range: -0.6426

Max Act: 0.6426. Min Act: -0.0000

Data Index: 474444 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.6116. Min Act: -0.0000

Data Index: 1046401 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.6394. Min Act: -0.0000

Data Index: 530412 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.5677. Min Act: -0.0000

Data Index: 1235873 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.5487. Min Act: -0.0000

Data Index: 798610 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.5621. Min Act: 0.0001

Data Index: 236551 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.5589. Min Act: -0.0000

Data Index: 535458 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.5485. Min Act: -0.0000

Data Index: 191624 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.5389. Min Act: -0.0000

Data Index: 784187 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1150843 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.5152. Min Act: -0.0000

Data Index: 874576 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.4844. Min Act: -0.0000

Data Index: 215568 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.5112. Min Act: -0.0000

Data Index: 659423 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.5250. Min Act: -0.0000

Data Index: 555456 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.4808. Min Act: -0.0000

Data Index: 1320831 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.4872. Min Act: -0.0000

Data Index: 52542 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.4648. Min Act: -0.0000

Data Index: 292523 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.4663. Min Act: -0.0000

Data Index: 1128192 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.4770. Min Act: -0.0000

Data Index: 679821 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 0.6426. Min Range: -0.6426

Max Act: 0.4603. Min Act: -0.0000

Data Index: 1115214 (C4 (Web Text))

Max Activating Token Index: 929