Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1216 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0604. Min Act: -0.0003

Data Index: 860493 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0586. Min Act: -0.0003

Data Index: 135719 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0588. Min Act: -0.0001

Data Index: 690330 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0556. Min Act: -0.0003

Data Index: 1145299 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0544. Min Act: -0.0000

Data Index: 1028202 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0544. Min Act: -0.0003

Data Index: 953225 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0520. Min Act: -0.0003

Data Index: 1287512 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0514. Min Act: -0.0003

Data Index: 460219 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0516. Min Act: -0.0003

Data Index: 963239 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0511. Min Act: -0.0003

Data Index: 896388 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0515. Min Act: -0.0003

Data Index: 166541 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0504. Min Act: -0.0003

Data Index: 1148331 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0502. Min Act: -0.0003

Data Index: 978021 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0501. Min Act: -0.0003

Data Index: 851134 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0502. Min Act: -0.0003

Data Index: 164102 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0506. Min Act: -0.0003

Data Index: 538841 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0497. Min Act: -0.0003

Data Index: 92100 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0503. Min Act: -0.0001

Data Index: 1130487 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0483. Min Act: -0.0003

Data Index: 471509 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0488. Min Act: -0.0003

Data Index: 1038116 (C4 (Web Text))

Max Activating Token Index: 1013