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

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

Neuron 3262 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5321. Min Range: -1.5321

Max Act: 1.4110. Min Act: -0.0001

Data Index: 751410 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 1.5321. Min Range: -1.5321

Max Act: 1.5321. Min Act: -0.0001

Data Index: 743124 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 1.5321. Min Range: -1.5321

Max Act: 1.4182. Min Act: -0.0001

Data Index: 1198049 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 1.5321. Min Range: -1.5321

Max Act: 1.1950. Min Act: -0.0001

Data Index: 812018 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 1.5321. Min Range: -1.5321

Max Act: 1.3047. Min Act: -0.0001

Data Index: 1308094 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 1.5321. Min Range: -1.5321

Max Act: 1.2462. Min Act: -0.0001

Data Index: 1057174 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 1.5321. Min Range: -1.5321

Max Act: 1.4248. Min Act: -0.0001

Data Index: 290805 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 1.5321. Min Range: -1.5321

Max Act: 1.1950. Min Act: -0.0001

Data Index: 302673 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 1.5321. Min Range: -1.5321

Max Act: 1.1409. Min Act: -0.0001

Data Index: 1131960 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 1.5321. Min Range: -1.5321

Max Act: 1.2078. Min Act: -0.0001

Data Index: 1313397 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 1.5321. Min Range: -1.5321

Max Act: 1.2714. Min Act: -0.0001

Data Index: 978276 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 1.5321. Min Range: -1.5321

Max Act: 1.3340. Min Act: -0.0001

Data Index: 549417 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 1.5321. Min Range: -1.5321

Max Act: 1.1665. Min Act: -0.0001

Data Index: 132423 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 1.5321. Min Range: -1.5321

Max Act: 1.1217. Min Act: -0.0001

Data Index: 138880 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 1.5321. Min Range: -1.5321

Max Act: 1.1713. Min Act: -0.0000

Data Index: 64135 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 1.5321. Min Range: -1.5321

Max Act: 1.0050. Min Act: -0.0001

Data Index: 663498 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 1.5321. Min Range: -1.5321

Max Act: 1.0166. Min Act: -0.0000

Data Index: 1024194 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 1.5321. Min Range: -1.5321

Max Act: 1.1207. Min Act: -0.0001

Data Index: 380440 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 1.5321. Min Range: -1.5321

Max Act: 1.1546. Min Act: -0.0001

Data Index: 664367 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 1.5321. Min Range: -1.5321

Max Act: 1.0486. Min Act: -0.0001

Data Index: 1135305 (C4 (Web Text))

Max Activating Token Index: 7