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

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

Neuron 672 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: 0.0570. Min Range: -0.0570

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1469158 (Python Code)

Max Activating Token Index: 964

Text #1

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0533. Min Act: -0.0003

Data Index: 1594007 (Python Code)

Max Activating Token Index: 717

Text #2

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0565. Min Act: -0.0003

Data Index: 350675 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0540. Min Act: -0.0003

Data Index: 1471219 (Python Code)

Max Activating Token Index: 236

Text #4

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0532. Min Act: -0.0002

Data Index: 125230 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0462. Min Act: -0.0003

Data Index: 1158741 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0498. Min Act: -0.0003

Data Index: 605785 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0511. Min Act: -0.0003

Data Index: 998832 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0504. Min Act: -0.0003

Data Index: 113221 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0523. Min Act: -0.0002

Data Index: 698987 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0480. Min Act: -0.0003

Data Index: 1297540 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0499. Min Act: -0.0003

Data Index: 1098578 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0497. Min Act: -0.0002

Data Index: 679632 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0497. Min Act: -0.0003

Data Index: 1557505 (Python Code)

Max Activating Token Index: 777

Text #14

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0496. Min Act: -0.0002

Data Index: 1472199 (Python Code)

Max Activating Token Index: 761

Text #15

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0493. Min Act: -0.0002

Data Index: 483239 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0508. Min Act: -0.0003

Data Index: 817406 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0470. Min Act: -0.0003

Data Index: 859493 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0500. Min Act: -0.0004

Data Index: 658561 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0469. Min Act: -0.0004

Data Index: 1235553 (C4 (Web Text))

Max Activating Token Index: 860