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

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

Neuron 1357 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1787. Min Act: -0.0002

Data Index: 1078179 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1733. Min Act: -0.0003

Data Index: 1335598 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1525. Min Act: -0.0003

Data Index: 47601 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1461. Min Act: -0.0003

Data Index: 277995 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1509. Min Act: -0.0003

Data Index: 467039 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1472. Min Act: -0.0003

Data Index: 729553 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1464. Min Act: -0.0003

Data Index: 539542 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1439. Min Act: -0.0003

Data Index: 889409 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1421. Min Act: -0.0003

Data Index: 131982 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1418. Min Act: -0.0003

Data Index: 1034384 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1412. Min Act: -0.0003

Data Index: 250567 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1402. Min Act: -0.0003

Data Index: 1258786 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1395. Min Act: -0.0003

Data Index: 605490 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1394. Min Act: -0.0003

Data Index: 902307 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1313. Min Act: -0.0003

Data Index: 357710 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1349. Min Act: -0.0003

Data Index: 1181964 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1384. Min Act: -0.0003

Data Index: 790443 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1316. Min Act: -0.0003

Data Index: 217272 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1317. Min Act: -0.0003

Data Index: 1269309 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1313. Min Act: -0.0003

Data Index: 468615 (C4 (Web Text))

Max Activating Token Index: 302