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

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

Neuron 5299 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0411. Min Act: -0.0000

Data Index: 923036 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0446. Min Act: -0.0000

Data Index: 600596 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0460. Min Act: -0.0000

Data Index: 463314 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0436. Min Act: -0.0000

Data Index: 362233 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0430. Min Act: -0.0000

Data Index: 863371 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0405. Min Act: -0.0000

Data Index: 445561 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0398. Min Act: -0.0000

Data Index: 1312193 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0386. Min Act: -0.0000

Data Index: 351436 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0389. Min Act: -0.0000

Data Index: 969451 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0417. Min Act: -0.0000

Data Index: 320302 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0363. Min Act: -0.0000

Data Index: 1411579 (Python Code)

Max Activating Token Index: 47

Text #11

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0389. Min Act: -0.0000

Data Index: 1132362 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0366. Min Act: -0.0000

Data Index: 1378764 (Python Code)

Max Activating Token Index: 30

Text #13

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0359. Min Act: -0.0000

Data Index: 1141210 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0356. Min Act: -0.0000

Data Index: 905401 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0355. Min Act: -0.0000

Data Index: 793016 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0362. Min Act: -0.0000

Data Index: 149177 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0348. Min Act: -0.0000

Data Index: 189973 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0357. Min Act: -0.0000

Data Index: 1507412 (Python Code)

Max Activating Token Index: 70

Text #19

Max Range: 0.0460. Min Range: -0.0460

Max Act: 0.0358. Min Act: -0.0000

Data Index: 117773 (C4 (Web Text))

Max Activating Token Index: 45