Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1918 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.2257. Min Act: -0.0001

Data Index: 613474 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1776. Min Act: -0.0001

Data Index: 1540082 (Python Code)

Max Activating Token Index: 738

Text #2

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.2038. Min Act: -0.0001

Data Index: 1509508 (Python Code)

Max Activating Token Index: 791

Text #3

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1743. Min Act: -0.0001

Data Index: 1458115 (Python Code)

Max Activating Token Index: 508

Text #4

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1734. Min Act: -0.0000

Data Index: 663348 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1682. Min Act: -0.0001

Data Index: 1213624 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1565. Min Act: -0.0001

Data Index: 1644504 (Python Code)

Max Activating Token Index: 478

Text #7

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1609. Min Act: -0.0001

Data Index: 1469888 (Python Code)

Max Activating Token Index: 328

Text #8

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1576. Min Act: -0.0001

Data Index: 1531563 (Python Code)

Max Activating Token Index: 717

Text #9

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1575. Min Act: -0.0001

Data Index: 1628329 (Python Code)

Max Activating Token Index: 375

Text #10

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1510. Min Act: -0.0001

Data Index: 135170 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1532. Min Act: -0.0000

Data Index: 1109416 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1578. Min Act: -0.0000

Data Index: 144195 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1459. Min Act: -0.0001

Data Index: 1522175 (Python Code)

Max Activating Token Index: 412

Text #14

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1456. Min Act: -0.0001

Data Index: 1656473 (Python Code)

Max Activating Token Index: 77

Text #15

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1454. Min Act: -0.0001

Data Index: 1462461 (Python Code)

Max Activating Token Index: 970

Text #16

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1444. Min Act: -0.0001

Data Index: 1468272 (Python Code)

Max Activating Token Index: 161

Text #17

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1418. Min Act: -0.0001

Data Index: 1652511 (Python Code)

Max Activating Token Index: 686

Text #18

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1418. Min Act: -0.0001

Data Index: 1447509 (Python Code)

Max Activating Token Index: 863

Text #19

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1490. Min Act: -0.0001

Data Index: 1547197 (Python Code)

Max Activating Token Index: 940