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

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

Neuron 3190 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: 0.2121. Min Range: -0.2121

Max Act: 0.2121. Min Act: -0.0001

Data Index: 629444 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.2041. Min Act: -0.0001

Data Index: 872868 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1689. Min Act: -0.0001

Data Index: 1169806 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1486. Min Act: -0.0001

Data Index: 670122 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1705. Min Act: -0.0001

Data Index: 280637 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1484. Min Act: -0.0001

Data Index: 567745 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1499. Min Act: -0.0001

Data Index: 317240 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1604. Min Act: -0.0001

Data Index: 35630 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1477. Min Act: -0.0001

Data Index: 1007205 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1508. Min Act: -0.0001

Data Index: 726184 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1453. Min Act: -0.0001

Data Index: 1213712 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1516. Min Act: -0.0001

Data Index: 1227921 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1403. Min Act: -0.0001

Data Index: 1274835 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1437. Min Act: -0.0001

Data Index: 808129 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1418. Min Act: -0.0001

Data Index: 6600 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1269. Min Act: -0.0001

Data Index: 600323 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1302. Min Act: -0.0001

Data Index: 384709 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1392. Min Act: -0.0001

Data Index: 558165 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1338. Min Act: -0.0001

Data Index: 1265966 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1380. Min Act: -0.0001

Data Index: 344784 (C4 (Web Text))

Max Activating Token Index: 987