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

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

Neuron 1342 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: 0.3358. Min Range: -0.3358

Max Act: 0.3358. Min Act: -0.0000

Data Index: 964594 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.3184. Min Act: -0.0000

Data Index: 620741 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.3192. Min Act: -0.0000

Data Index: 314041 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2746. Min Act: -0.0001

Data Index: 810206 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2732. Min Act: -0.0000

Data Index: 993517 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2686. Min Act: 0.0000

Data Index: 110187 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2774. Min Act: -0.0000

Data Index: 1057471 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2599. Min Act: -0.0000

Data Index: 747306 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2574. Min Act: -0.0000

Data Index: 563588 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2450. Min Act: -0.0000

Data Index: 34942 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2558. Min Act: -0.0000

Data Index: 624900 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2551. Min Act: -0.0000

Data Index: 678147 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2512. Min Act: -0.0000

Data Index: 901802 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2436. Min Act: -0.0000

Data Index: 347186 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2608. Min Act: -0.0000

Data Index: 470702 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2416. Min Act: -0.0001

Data Index: 784360 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1214150 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2419. Min Act: -0.0000

Data Index: 775444 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2308. Min Act: -0.0000

Data Index: 720320 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2453. Min Act: 0.0000

Data Index: 1276765 (C4 (Web Text))

Max Activating Token Index: 958