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

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

Neuron 1833 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1699. Min Act: -0.0000

Data Index: 927228 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1416. Min Act: -0.0000

Data Index: 739559 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1588. Min Act: -0.0000

Data Index: 564148 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1603. Min Act: -0.0000

Data Index: 1512933 (Python Code)

Max Activating Token Index: 307

Text #4

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1497. Min Act: -0.0000

Data Index: 177315 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1441. Min Act: -0.0000

Data Index: 964068 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1417. Min Act: -0.0000

Data Index: 874382 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1464. Min Act: -0.0000

Data Index: 227226 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1411. Min Act: -0.0000

Data Index: 1106848 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1277. Min Act: -0.0000

Data Index: 76250 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1431. Min Act: -0.0000

Data Index: 224874 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1304. Min Act: -0.0000

Data Index: 106826 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1335. Min Act: -0.0000

Data Index: 448799 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1428. Min Act: -0.0000

Data Index: 268918 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1295. Min Act: -0.0000

Data Index: 1252561 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1304. Min Act: -0.0000

Data Index: 830464 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1308. Min Act: -0.0000

Data Index: 907545 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1135. Min Act: -0.0001

Data Index: 1304526 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1627318 (Python Code)

Max Activating Token Index: 196

Text #19

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1333. Min Act: -0.0000

Data Index: 485272 (C4 (Web Text))

Max Activating Token Index: 1014