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

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

Neuron 5080 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1796. Min Act: -0.0002

Data Index: 760870 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1609. Min Act: -0.0002

Data Index: 667152 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1513. Min Act: -0.0003

Data Index: 1081609 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1520. Min Act: -0.0002

Data Index: 647313 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1448. Min Act: -0.0003

Data Index: 1314265 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1413. Min Act: -0.0002

Data Index: 428262 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1426. Min Act: -0.0003

Data Index: 829029 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1418. Min Act: -0.0002

Data Index: 1170674 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1404. Min Act: -0.0002

Data Index: 510515 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1392. Min Act: -0.0002

Data Index: 546127 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1393. Min Act: -0.0002

Data Index: 86757 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1396. Min Act: -0.0003

Data Index: 10509 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1311. Min Act: -0.0002

Data Index: 637879 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1359. Min Act: -0.0002

Data Index: 276356 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1358. Min Act: -0.0002

Data Index: 378324 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1329. Min Act: -0.0002

Data Index: 916464 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1343. Min Act: -0.0002

Data Index: 741142 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1357. Min Act: -0.0002

Data Index: 329955 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1334. Min Act: -0.0003

Data Index: 269764 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.1796. Min Range: -0.1796

Max Act: 0.1331. Min Act: -0.0002

Data Index: 1309636 (C4 (Web Text))

Max Activating Token Index: 398