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

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

Neuron 601 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3234. Min Range: -3.3234

Max Act: 3.1762. Min Act: -0.0001

Data Index: 65804 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 3.3234. Min Range: -3.3234

Max Act: 3.3041. Min Act: -0.0001

Data Index: 1155029 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 3.3234. Min Range: -3.3234

Max Act: 3.3234. Min Act: -0.0001

Data Index: 1322687 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 3.3234. Min Range: -3.3234

Max Act: 3.1384. Min Act: -0.0001

Data Index: 561535 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.9697. Min Act: -0.0001

Data Index: 374909 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 3.3234. Min Range: -3.3234

Max Act: 3.0431. Min Act: -0.0001

Data Index: 110220 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 3.3234. Min Range: -3.3234

Max Act: 3.0196. Min Act: -0.0001

Data Index: 1287967 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 3.3234. Min Range: -3.3234

Max Act: 3.1692. Min Act: -0.0001

Data Index: 695634 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.9862. Min Act: -0.0001

Data Index: 1239188 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.8279. Min Act: -0.0001

Data Index: 1347985 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.9583. Min Act: -0.0001

Data Index: 997320 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 3.3234. Min Range: -3.3234

Max Act: 3.0621. Min Act: -0.0001

Data Index: 84268 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.8064. Min Act: -0.0001

Data Index: 1213093 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.9593. Min Act: -0.0001

Data Index: 947311 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.9313. Min Act: -0.0001

Data Index: 229096 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.7833. Min Act: -0.0001

Data Index: 157412 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.9194. Min Act: -0.0001

Data Index: 81126 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.6425. Min Act: -0.0001

Data Index: 1201024 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.8623. Min Act: -0.0001

Data Index: 1310272 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 3.3234. Min Range: -3.3234

Max Act: 2.7243. Min Act: -0.0001

Data Index: 222204 (C4 (Web Text))

Max Activating Token Index: 808