Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3486 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.7373. Min Range: -4.7373

Max Act: 4.7373. Min Act: -0.0000

Data Index: 676719 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 4.7373. Min Range: -4.7373

Max Act: 4.3487. Min Act: -0.0000

Data Index: 453206 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 4.7373. Min Range: -4.7373

Max Act: 3.5722. Min Act: -0.0000

Data Index: 698786 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 4.7373. Min Range: -4.7373

Max Act: 4.4588. Min Act: -0.0000

Data Index: 408700 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 4.7373. Min Range: -4.7373

Max Act: 3.8582. Min Act: -0.0000

Data Index: 809737 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 4.7373. Min Range: -4.7373

Max Act: 4.3697. Min Act: -0.0000

Data Index: 1177874 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 4.7373. Min Range: -4.7373

Max Act: 3.8674. Min Act: -0.0000

Data Index: 280431 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 4.7373. Min Range: -4.7373

Max Act: 3.6297. Min Act: -0.0000

Data Index: 348597 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 4.7373. Min Range: -4.7373

Max Act: 4.2269. Min Act: -0.0000

Data Index: 867797 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 4.7373. Min Range: -4.7373

Max Act: 3.8581. Min Act: -0.0000

Data Index: 1319470 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 4.7373. Min Range: -4.7373

Max Act: 3.9653. Min Act: -0.0000

Data Index: 1103833 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 4.7373. Min Range: -4.7373

Max Act: 3.7234. Min Act: -0.0000

Data Index: 1295454 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 4.7373. Min Range: -4.7373

Max Act: 3.6954. Min Act: -0.0000

Data Index: 71946 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 4.7373. Min Range: -4.7373

Max Act: 3.3378. Min Act: -0.0000

Data Index: 4626 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 4.7373. Min Range: -4.7373

Max Act: 3.8313. Min Act: -0.0000

Data Index: 117533 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 4.7373. Min Range: -4.7373

Max Act: 4.1348. Min Act: -0.0000

Data Index: 79438 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 4.7373. Min Range: -4.7373

Max Act: 3.8214. Min Act: -0.0000

Data Index: 661064 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 4.7373. Min Range: -4.7373

Max Act: 3.7194. Min Act: -0.0000

Data Index: 627755 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 4.7373. Min Range: -4.7373

Max Act: 3.5397. Min Act: -0.0000

Data Index: 1066051 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 4.7373. Min Range: -4.7373

Max Act: 3.8364. Min Act: -0.0000

Data Index: 150643 (C4 (Web Text))

Max Activating Token Index: 911