Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1004 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1560. Min Act: -0.0001

Data Index: 807702 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1415. Min Act: -0.0001

Data Index: 943572 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1462. Min Act: -0.0001

Data Index: 279801 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1374. Min Act: -0.0001

Data Index: 966366 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1375. Min Act: -0.0001

Data Index: 443341 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1371. Min Act: -0.0001

Data Index: 578304 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1366. Min Act: -0.0001

Data Index: 452980 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1399. Min Act: -0.0001

Data Index: 1330583 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1375. Min Act: -0.0001

Data Index: 660977 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1340. Min Act: -0.0001

Data Index: 149421 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1241. Min Act: -0.0001

Data Index: 407836 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1289. Min Act: -0.0001

Data Index: 1185412 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1287. Min Act: -0.0001

Data Index: 1311792 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1229. Min Act: -0.0001

Data Index: 676056 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1242. Min Act: -0.0001

Data Index: 721686 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1224. Min Act: -0.0001

Data Index: 816504 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1192. Min Act: -0.0001

Data Index: 948615 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1214. Min Act: -0.0001

Data Index: 1347222 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1177. Min Act: -0.0001

Data Index: 94459 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1012. Min Act: -0.0001

Data Index: 541492 (C4 (Web Text))

Max Activating Token Index: 619