Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3599 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1400. Min Act: -0.0001

Data Index: 942944 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1319. Min Act: -0.0001

Data Index: 756342 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1298. Min Act: -0.0001

Data Index: 245539 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1258. Min Act: -0.0000

Data Index: 340867 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1299. Min Act: -0.0000

Data Index: 875186 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1202. Min Act: -0.0001

Data Index: 618825 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1243. Min Act: -0.0000

Data Index: 20857 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1228. Min Act: -0.0001

Data Index: 326231 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1222. Min Act: -0.0000

Data Index: 1121922 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1245. Min Act: -0.0000

Data Index: 1280659 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1204. Min Act: -0.0000

Data Index: 447434 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1196. Min Act: -0.0001

Data Index: 594142 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1234. Min Act: -0.0001

Data Index: 158088 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1187. Min Act: -0.0001

Data Index: 1309443 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1232. Min Act: -0.0000

Data Index: 1263144 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1121. Min Act: -0.0000

Data Index: 664443 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1051. Min Act: -0.0000

Data Index: 965489 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1009. Min Act: -0.0001

Data Index: 167638 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1085. Min Act: -0.0001

Data Index: 15467 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 0.1400. Min Range: -0.1400

Max Act: 0.1120. Min Act: -0.0001

Data Index: 1551622 (Python Code)

Max Activating Token Index: 634