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

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

Neuron 808 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: 0.2091. Min Range: -0.2091

Max Act: 0.2091. Min Act: -0.0002

Data Index: 28215 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1776. Min Act: -0.0002

Data Index: 942520 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1675. Min Act: -0.0002

Data Index: 706261 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1940. Min Act: -0.0001

Data Index: 416294 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1699. Min Act: -0.0001

Data Index: 436950 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1589. Min Act: -0.0002

Data Index: 714020 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1720. Min Act: -0.0002

Data Index: 634129 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1592. Min Act: -0.0001

Data Index: 794656 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1630. Min Act: -0.0001

Data Index: 426 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1529. Min Act: -0.0002

Data Index: 1090594 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1619. Min Act: -0.0001

Data Index: 965092 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1584. Min Act: -0.0002

Data Index: 95051 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1487. Min Act: -0.0001

Data Index: 144129 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1599. Min Act: -0.0002

Data Index: 972880 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1528. Min Act: -0.0002

Data Index: 245220 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1526. Min Act: -0.0001

Data Index: 201610 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1582. Min Act: -0.0002

Data Index: 1325242 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1588. Min Act: -0.0002

Data Index: 533430 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1648. Min Act: -0.0001

Data Index: 333135 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1632. Min Act: -0.0001

Data Index: 452307 (C4 (Web Text))

Max Activating Token Index: 171