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

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

Neuron 2660 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: 0.1471. Min Range: -0.1471

Max Act: 0.1471. Min Act: -0.0001

Data Index: 1295680 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1422. Min Act: -0.0001

Data Index: 524445 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1402. Min Act: -0.0001

Data Index: 519017 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1396. Min Act: -0.0001

Data Index: 390587 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1411. Min Act: -0.0001

Data Index: 283069 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1359. Min Act: -0.0001

Data Index: 709819 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1368. Min Act: -0.0001

Data Index: 654441 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1425. Min Act: -0.0001

Data Index: 1085913 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1379. Min Act: -0.0001

Data Index: 230572 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1367. Min Act: -0.0001

Data Index: 981228 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1311. Min Act: -0.0001

Data Index: 746517 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1359. Min Act: -0.0001

Data Index: 288188 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1319. Min Act: -0.0001

Data Index: 48431 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1356. Min Act: -0.0001

Data Index: 1024454 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1213040 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1303. Min Act: -0.0001

Data Index: 1156461 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1323. Min Act: -0.0001

Data Index: 501924 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1287. Min Act: -0.0001

Data Index: 950801 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1334. Min Act: -0.0001

Data Index: 609575 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1312. Min Act: -0.0001

Data Index: 1352443 (C4 (Web Text))

Max Activating Token Index: 958