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

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

Neuron 805 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2257. Min Range: -4.2257

Max Act: 4.2257. Min Act: -0.0000

Data Index: 1453283 (Python Code)

Max Activating Token Index: 487

Text #1

Max Range: 4.2257. Min Range: -4.2257

Max Act: 3.8879. Min Act: -0.0000

Data Index: 1451340 (Python Code)

Max Activating Token Index: 316

Text #2

Max Range: 4.2257. Min Range: -4.2257

Max Act: 3.2475. Min Act: -0.0000

Data Index: 1476650 (Python Code)

Max Activating Token Index: 72

Text #3

Max Range: 4.2257. Min Range: -4.2257

Max Act: 3.4398. Min Act: -0.0000

Data Index: 1463911 (Python Code)

Max Activating Token Index: 858

Text #4

Max Range: 4.2257. Min Range: -4.2257

Max Act: 3.0626. Min Act: -0.0000

Data Index: 1516815 (Python Code)

Max Activating Token Index: 961

Text #5

Max Range: 4.2257. Min Range: -4.2257

Max Act: 3.2615. Min Act: -0.0000

Data Index: 1437798 (Python Code)

Max Activating Token Index: 875

Text #6

Max Range: 4.2257. Min Range: -4.2257

Max Act: 2.9726. Min Act: -0.0000

Data Index: 1605533 (Python Code)

Max Activating Token Index: 410

Text #7

Max Range: 4.2257. Min Range: -4.2257

Max Act: 2.9302. Min Act: -0.0000

Data Index: 1605818 (Python Code)

Max Activating Token Index: 567

Text #8

Max Range: 4.2257. Min Range: -4.2257

Max Act: 2.9115. Min Act: -0.0000

Data Index: 1651847 (Python Code)

Max Activating Token Index: 580

Text #9

Max Range: 4.2257. Min Range: -4.2257

Max Act: 2.9046. Min Act: -0.0000

Data Index: 1361194 (Python Code)

Max Activating Token Index: 624

Text #10

Max Range: 4.2257. Min Range: -4.2257

Max Act: 2.7626. Min Act: -0.0000

Data Index: 1601996 (Python Code)

Max Activating Token Index: 918

Text #11

Max Range: 4.2257. Min Range: -4.2257

Max Act: 3.0414. Min Act: -0.0000

Data Index: 1500241 (Python Code)

Max Activating Token Index: 569

Text #12

Max Range: 4.2257. Min Range: -4.2257

Max Act: 3.0235. Min Act: -0.0000

Data Index: 1523904 (Python Code)

Max Activating Token Index: 609

Text #13

Max Range: 4.2257. Min Range: -4.2257

Max Act: 2.7279. Min Act: -0.0000

Data Index: 1512457 (Python Code)

Max Activating Token Index: 370

Text #14

Max Range: 4.2257. Min Range: -4.2257

Max Act: 2.8591. Min Act: -0.0000

Data Index: 1504672 (Python Code)

Max Activating Token Index: 628

Text #15

Max Range: 4.2257. Min Range: -4.2257

Max Act: 2.8556. Min Act: -0.0000

Data Index: 1568691 (Python Code)

Max Activating Token Index: 960

Text #16

Max Range: 4.2257. Min Range: -4.2257

Max Act: 2.8344. Min Act: -0.0000

Data Index: 1589493 (Python Code)

Max Activating Token Index: 526

Text #17

Max Range: 4.2257. Min Range: -4.2257

Max Act: 2.7843. Min Act: -0.0000

Data Index: 1509891 (Python Code)

Max Activating Token Index: 898

Text #18

Max Range: 4.2257. Min Range: -4.2257

Max Act: 2.7608. Min Act: -0.0000

Data Index: 1476237 (Python Code)

Max Activating Token Index: 255

Text #19

Max Range: 4.2257. Min Range: -4.2257

Max Act: 2.7346. Min Act: -0.0000

Data Index: 1548234 (Python Code)

Max Activating Token Index: 209