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

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

Neuron 2288 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: 0.5417. Min Range: -0.5417

Max Act: 0.5290. Min Act: -0.0002

Data Index: 765416 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.5342. Min Act: -0.0002

Data Index: 104294 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.5334. Min Act: -0.0001

Data Index: 258535 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4959. Min Act: -0.0002

Data Index: 765720 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.5417. Min Act: -0.0001

Data Index: 895191 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.5088. Min Act: -0.0002

Data Index: 685440 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.5022. Min Act: -0.0001

Data Index: 963384 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4655. Min Act: -0.0001

Data Index: 76033 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4597. Min Act: -0.0001

Data Index: 1226264 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4648. Min Act: -0.0001

Data Index: 1268976 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.5157. Min Act: -0.0001

Data Index: 1044495 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4539. Min Act: -0.0002

Data Index: 936110 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4615. Min Act: -0.0002

Data Index: 1109321 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4566. Min Act: -0.0001

Data Index: 768659 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4964. Min Act: -0.0001

Data Index: 744266 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4811. Min Act: -0.0002

Data Index: 253447 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4384. Min Act: -0.0002

Data Index: 751014 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4635. Min Act: -0.0001

Data Index: 240566 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4316. Min Act: -0.0002

Data Index: 145957 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4672. Min Act: -0.0001

Data Index: 85444 (C4 (Web Text))

Max Activating Token Index: 724