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

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

Neuron 70 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.2301. Min Act: -0.0003

Data Index: 7386 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.1013. Min Act: -0.0003

Data Index: 263539 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.0681. Min Act: -0.0003

Data Index: 60734 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.0424. Min Act: -0.0003

Data Index: 1272445 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.0698. Min Act: -0.0003

Data Index: 612419 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.0387. Min Act: -0.0003

Data Index: 1266191 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.0808. Min Act: -0.0003

Data Index: 77797 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.9992. Min Act: -0.0003

Data Index: 782181 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.0288. Min Act: -0.0003

Data Index: 34272 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 1.2301. Min Range: -1.2301

Max Act: 1.0182. Min Act: -0.0003

Data Index: 19456 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.9863. Min Act: -0.0003

Data Index: 282812 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.9703. Min Act: -0.0003

Data Index: 1265762 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.9641. Min Act: -0.0003

Data Index: 170627 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.9331. Min Act: -0.0003

Data Index: 1089796 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.9343. Min Act: -0.0003

Data Index: 1285140 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.9326. Min Act: -0.0003

Data Index: 1238211 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.9035. Min Act: -0.0003

Data Index: 1325024 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.9303. Min Act: -0.0003

Data Index: 741961 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.9265. Min Act: -0.0003

Data Index: 1027344 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 1.2301. Min Range: -1.2301

Max Act: 0.8954. Min Act: -0.0003

Data Index: 1249623 (C4 (Web Text))

Max Activating Token Index: 137