Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2727 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1304. Min Range: -2.1304

Max Act: 2.1304. Min Act: -0.0000

Data Index: 396772 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 2.1304. Min Range: -2.1304

Max Act: 2.0487. Min Act: -0.0000

Data Index: 1515928 (Python Code)

Max Activating Token Index: 568

Text #2

Max Range: 2.1304. Min Range: -2.1304

Max Act: 2.0298. Min Act: -0.0000

Data Index: 1272206 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 2.1304. Min Range: -2.1304

Max Act: 2.0393. Min Act: -0.0000

Data Index: 973697 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 2.1304. Min Range: -2.1304

Max Act: 1.9208. Min Act: -0.0000

Data Index: 1482545 (Python Code)

Max Activating Token Index: 872

Text #5

Max Range: 2.1304. Min Range: -2.1304

Max Act: 1.9136. Min Act: -0.0000

Data Index: 1571817 (Python Code)

Max Activating Token Index: 425

Text #6

Max Range: 2.1304. Min Range: -2.1304

Max Act: 1.8955. Min Act: -0.0000

Data Index: 1485465 (Python Code)

Max Activating Token Index: 202

Text #7

Max Range: 2.1304. Min Range: -2.1304

Max Act: 1.8954. Min Act: -0.0000

Data Index: 695081 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 2.1304. Min Range: -2.1304

Max Act: 1.8526. Min Act: -0.0000

Data Index: 1228156 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 2.1304. Min Range: -2.1304

Max Act: 1.8486. Min Act: -0.0000

Data Index: 1424681 (Python Code)

Max Activating Token Index: 252

Text #10

Max Range: 2.1304. Min Range: -2.1304

Max Act: 1.8211. Min Act: -0.0000

Data Index: 1552772 (Python Code)

Max Activating Token Index: 609

Text #11

Max Range: 2.1304. Min Range: -2.1304

Max Act: 1.8086. Min Act: -0.0000

Data Index: 63540 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 2.1304. Min Range: -2.1304

Max Act: 1.7812. Min Act: -0.0000

Data Index: 87954 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 2.1304. Min Range: -2.1304

Max Act: 1.6707. Min Act: -0.0000

Data Index: 1451763 (Python Code)

Max Activating Token Index: 579

Text #14

Max Range: 2.1304. Min Range: -2.1304

Max Act: 1.8598. Min Act: -0.0000

Data Index: 411656 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 2.1304. Min Range: -2.1304

Max Act: 1.7500. Min Act: -0.0000

Data Index: 1350078 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 2.1304. Min Range: -2.1304

Max Act: 1.8184. Min Act: -0.0000

Data Index: 674748 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 2.1304. Min Range: -2.1304

Max Act: 1.6241. Min Act: -0.0000

Data Index: 1339014 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 2.1304. Min Range: -2.1304

Max Act: 1.6205. Min Act: -0.0000

Data Index: 620124 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 2.1304. Min Range: -2.1304

Max Act: 1.7004. Min Act: -0.0000

Data Index: 1302632 (C4 (Web Text))

Max Activating Token Index: 960