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

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

Neuron 667 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.2640. Min Act: -0.0001

Data Index: 1656046 (Python Code)

Max Activating Token Index: 769

Text #1

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.2599. Min Act: -0.0001

Data Index: 1622028 (Python Code)

Max Activating Token Index: 536

Text #2

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.2607. Min Act: -0.0001

Data Index: 1588308 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1634371 (Python Code)

Max Activating Token Index: 32

Text #4

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.2587. Min Act: -0.0000

Data Index: 1582353 (Python Code)

Max Activating Token Index: 311

Text #5

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.2534. Min Act: -0.0000

Data Index: 1425697 (Python Code)

Max Activating Token Index: 484

Text #6

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.2430. Min Act: -0.0001

Data Index: 1615409 (Python Code)

Max Activating Token Index: 99

Text #7

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.2507. Min Act: -0.0001

Data Index: 1482640 (Python Code)

Max Activating Token Index: 722

Text #8

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.2335. Min Act: -0.0001

Data Index: 1391689 (Python Code)

Max Activating Token Index: 40

Text #9

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.2471. Min Act: -0.0001

Data Index: 1412957 (Python Code)

Max Activating Token Index: 83

Text #10

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.2406. Min Act: -0.0001

Data Index: 1451253 (Python Code)

Max Activating Token Index: 494

Text #11

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.2372. Min Act: -0.0001

Data Index: 1399063 (Python Code)

Max Activating Token Index: 394

Text #12

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.2454. Min Act: -0.0000

Data Index: 1465936 (Python Code)

Max Activating Token Index: 213

Text #13

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.2225. Min Act: -0.0001

Data Index: 1402591 (Python Code)

Max Activating Token Index: 765

Text #14

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.2266. Min Act: -0.0001

Data Index: 1627179 (Python Code)

Max Activating Token Index: 98

Text #15

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.2266. Min Act: -0.0001

Data Index: 1641369 (Python Code)

Max Activating Token Index: 50

Text #16

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.2245. Min Act: -0.0001

Data Index: 1469914 (Python Code)

Max Activating Token Index: 457

Text #17

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.2156. Min Act: -0.0001

Data Index: 1431916 (Python Code)

Max Activating Token Index: 285

Text #18

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.2209. Min Act: -0.0001

Data Index: 1412933 (Python Code)

Max Activating Token Index: 383

Text #19

Max Range: 0.2690. Min Range: -0.2690

Max Act: 0.2208. Min Act: -0.0001

Data Index: 1597384 (Python Code)

Max Activating Token Index: 557