Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2618 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.2201. Min Act: -0.0001

Data Index: 127881 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1854. Min Act: -0.0001

Data Index: 1110452 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1874. Min Act: -0.0001

Data Index: 106087 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1854. Min Act: -0.0000

Data Index: 646559 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1852. Min Act: -0.0001

Data Index: 747355 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1104180 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1797. Min Act: -0.0000

Data Index: 783398 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1773. Min Act: -0.0001

Data Index: 2829 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1714. Min Act: -0.0001

Data Index: 738175 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1614. Min Act: -0.0001

Data Index: 1194686 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1643. Min Act: -0.0000

Data Index: 905220 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1689. Min Act: -0.0001

Data Index: 1198317 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1679. Min Act: -0.0001

Data Index: 354516 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1726. Min Act: -0.0001

Data Index: 1197990 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1721. Min Act: -0.0001

Data Index: 1238592 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1645. Min Act: -0.0001

Data Index: 1084520 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1635. Min Act: -0.0001

Data Index: 55326 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1653. Min Act: -0.0000

Data Index: 484751 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1584. Min Act: -0.0001

Data Index: 1164989 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1639. Min Act: -0.0001

Data Index: 433906 (C4 (Web Text))

Max Activating Token Index: 332