Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1490 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0695. Min Act: -0.0000

Data Index: 833032 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0602. Min Act: -0.0000

Data Index: 548368 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0384. Min Act: -0.0000

Data Index: 641754 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0379. Min Act: 0.0000

Data Index: 1418294 (Python Code)

Max Activating Token Index: 871

Text #4

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0340. Min Act: -0.0000

Data Index: 69859 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0356. Min Act: -0.0000

Data Index: 744235 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0420. Min Act: -0.0000

Data Index: 757607 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0378. Min Act: -0.0000

Data Index: 1461134 (Python Code)

Max Activating Token Index: 1012

Text #8

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0359. Min Act: -0.0000

Data Index: 1361068 (Python Code)

Max Activating Token Index: 660

Text #9

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0363. Min Act: -0.0000

Data Index: 870483 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0323. Min Act: -0.0000

Data Index: 758660 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0365. Min Act: -0.0000

Data Index: 283482 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0352. Min Act: -0.0000

Data Index: 607555 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0445. Min Act: -0.0000

Data Index: 641122 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0340. Min Act: -0.0000

Data Index: 1492345 (Python Code)

Max Activating Token Index: 846

Text #15

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0328. Min Act: -0.0000

Data Index: 851271 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0271. Min Act: -0.0000

Data Index: 1228120 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0309. Min Act: -0.0000

Data Index: 31387 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0330. Min Act: -0.0000

Data Index: 325057 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0358. Min Act: -0.0000

Data Index: 619263 (C4 (Web Text))

Max Activating Token Index: 260