Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3783 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2578. Min Act: -0.0000

Data Index: 75496 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2325. Min Act: -0.0000

Data Index: 1073708 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2256. Min Act: -0.0000

Data Index: 794443 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2150. Min Act: -0.0000

Data Index: 350589 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2053. Min Act: -0.0000

Data Index: 99649 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2048. Min Act: -0.0000

Data Index: 1306853 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2110. Min Act: -0.0000

Data Index: 228959 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.2014. Min Act: -0.0000

Data Index: 191148 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1731. Min Act: -0.0000

Data Index: 1127671 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1675. Min Act: -0.0000

Data Index: 238131 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1708. Min Act: -0.0000

Data Index: 630943 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1666. Min Act: -0.0000

Data Index: 841031 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1664. Min Act: -0.0000

Data Index: 1219362 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1780. Min Act: -0.0000

Data Index: 585010 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1687. Min Act: -0.0000

Data Index: 391095 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1663. Min Act: -0.0000

Data Index: 590576 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1594. Min Act: -0.0000

Data Index: 693170 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1451. Min Act: -0.0000

Data Index: 1097583 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1488. Min Act: -0.0000

Data Index: 5849 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.2578. Min Range: -0.2578

Max Act: 0.1431. Min Act: -0.0000

Data Index: 1242975 (C4 (Web Text))

Max Activating Token Index: 697