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

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

Neuron 2519 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1427952 (Python Code)

Max Activating Token Index: 450

Text #1

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1497678 (Python Code)

Max Activating Token Index: 135

Text #2

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1450507 (Python Code)

Max Activating Token Index: 366

Text #3

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1624805 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1596662 (Python Code)

Max Activating Token Index: 594

Text #5

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0335. Min Act: -0.0002

Data Index: 1565481 (Python Code)

Max Activating Token Index: 481

Text #6

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0345. Min Act: -0.0002

Data Index: 1550706 (Python Code)

Max Activating Token Index: 18

Text #7

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1371660 (Python Code)

Max Activating Token Index: 466

Text #8

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1278833 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1526512 (Python Code)

Max Activating Token Index: 347

Text #10

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1448298 (Python Code)

Max Activating Token Index: 690

Text #11

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1651017 (Python Code)

Max Activating Token Index: 290

Text #12

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1453201 (Python Code)

Max Activating Token Index: 392

Text #13

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0332. Min Act: -0.0002

Data Index: 46183 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0338. Min Act: -0.0002

Data Index: 1572609 (Python Code)

Max Activating Token Index: 342

Text #15

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0328. Min Act: -0.0002

Data Index: 1461333 (Python Code)

Max Activating Token Index: 356

Text #16

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0338. Min Act: -0.0002

Data Index: 1413724 (Python Code)

Max Activating Token Index: 980

Text #17

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0288. Min Act: -0.0002

Data Index: 268544 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1575295 (Python Code)

Max Activating Token Index: 135

Text #19

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1563609 (Python Code)

Max Activating Token Index: 849