Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3660 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.3201. Min Act: -0.0001

Data Index: 633564 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.3399. Min Act: -0.0001

Data Index: 1085058 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.2550. Min Act: -0.0001

Data Index: 1344094 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.1770. Min Act: -0.0001

Data Index: 394132 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.2628. Min Act: -0.0001

Data Index: 1000615 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.1782. Min Act: -0.0001

Data Index: 204091 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.1695. Min Act: -0.0001

Data Index: 494183 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.1961. Min Act: -0.0001

Data Index: 142040 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.2119. Min Act: -0.0001

Data Index: 402940 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.2019. Min Act: -0.0001

Data Index: 516910 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.1042. Min Act: -0.0001

Data Index: 583796 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.1739. Min Act: -0.0001

Data Index: 982051 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.1536. Min Act: -0.0001

Data Index: 201845 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.1155. Min Act: -0.0001

Data Index: 884712 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.1205. Min Act: -0.0001

Data Index: 1205780 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.1715. Min Act: -0.0001

Data Index: 564299 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.0967. Min Act: -0.0001

Data Index: 575742 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.1808. Min Act: -0.0001

Data Index: 760236 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.1478. Min Act: -0.0001

Data Index: 95203 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.1075. Min Act: -0.0001

Data Index: 1224387 (C4 (Web Text))

Max Activating Token Index: 23