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

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

Neuron 1021 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0317. Min Act: -0.0002

Data Index: 482783 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0303. Min Act: -0.0002

Data Index: 80096 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0298. Min Act: -0.0002

Data Index: 483886 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0298. Min Act: -0.0002

Data Index: 488625 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0292. Min Act: -0.0002

Data Index: 943261 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0296. Min Act: -0.0002

Data Index: 743015 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0290. Min Act: -0.0002

Data Index: 728238 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0290. Min Act: -0.0002

Data Index: 1067514 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1024664 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0287. Min Act: -0.0002

Data Index: 170894 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0285. Min Act: -0.0002

Data Index: 996626 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0291. Min Act: -0.0002

Data Index: 595726 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0284. Min Act: -0.0002

Data Index: 265531 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1334837 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0283. Min Act: -0.0002

Data Index: 608144 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0283. Min Act: -0.0002

Data Index: 7796 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1095811 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0282. Min Act: -0.0002

Data Index: 364712 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1151754 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0282. Min Act: -0.0002

Data Index: 507221 (C4 (Web Text))

Max Activating Token Index: 336