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

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

Neuron 3099 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: 0.0725. Min Range: -0.0725

Max Act: 0.0725. Min Act: -0.0002

Data Index: 1307052 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0707. Min Act: -0.0002

Data Index: 1053122 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0666. Min Act: -0.0001

Data Index: 1130224 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0645. Min Act: -0.0001

Data Index: 512571 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0592. Min Act: -0.0001

Data Index: 937383 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0603. Min Act: -0.0002

Data Index: 675763 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1049711 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0583. Min Act: -0.0001

Data Index: 727998 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0588. Min Act: -0.0002

Data Index: 880533 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0573. Min Act: -0.0001

Data Index: 12055 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1043684 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1182402 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0523. Min Act: -0.0001

Data Index: 1154579 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0538. Min Act: -0.0002

Data Index: 338737 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0561. Min Act: -0.0001

Data Index: 1218620 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0504. Min Act: -0.0002

Data Index: 453601 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0533. Min Act: -0.0002

Data Index: 61561 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0587. Min Act: -0.0002

Data Index: 259418 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0575. Min Act: -0.0001

Data Index: 1015657 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0554. Min Act: -0.0002

Data Index: 542725 (C4 (Web Text))

Max Activating Token Index: 552