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

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

Neuron 1003 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: 0.5911. Min Range: -0.5911

Max Act: 0.5911. Min Act: 0.0000

Data Index: 1549494 (Python Code)

Max Activating Token Index: 248

Text #1

Max Range: 0.5911. Min Range: -0.5911

Max Act: 0.5553. Min Act: 0.0000

Data Index: 1453820 (Python Code)

Max Activating Token Index: 91

Text #2

Max Range: 0.5911. Min Range: -0.5911

Max Act: 0.5674. Min Act: 0.0000

Data Index: 1385928 (Python Code)

Max Activating Token Index: 887

Text #3

Max Range: 0.5911. Min Range: -0.5911

Max Act: 0.5453. Min Act: 0.0000

Data Index: 1633228 (Python Code)

Max Activating Token Index: 140

Text #4

Max Range: 0.5911. Min Range: -0.5911

Max Act: 0.5765. Min Act: 0.0000

Data Index: 1490609 (Python Code)

Max Activating Token Index: 187

Text #5

Max Range: 0.5911. Min Range: -0.5911

Max Act: 0.5517. Min Act: 0.0000

Data Index: 1390007 (Python Code)

Max Activating Token Index: 843

Text #6

Max Range: 0.5911. Min Range: -0.5911

Max Act: 0.5441. Min Act: -0.0000

Data Index: 1502605 (Python Code)

Max Activating Token Index: 528

Text #7

Max Range: 0.5911. Min Range: -0.5911

Max Act: 0.5401. Min Act: 0.0000

Data Index: 1519210 (Python Code)

Max Activating Token Index: 666

Text #8

Max Range: 0.5911. Min Range: -0.5911

Max Act: 0.5395. Min Act: 0.0000

Data Index: 1584277 (Python Code)

Max Activating Token Index: 386

Text #9

Max Range: 0.5911. Min Range: -0.5911

Max Act: 0.5334. Min Act: 0.0000

Data Index: 1439839 (Python Code)

Max Activating Token Index: 150

Text #10

Max Range: 0.5911. Min Range: -0.5911

Max Act: 0.5321. Min Act: 0.0000

Data Index: 1578848 (Python Code)

Max Activating Token Index: 344

Text #11

Max Range: 0.5911. Min Range: -0.5911

Max Act: 0.5317. Min Act: 0.0000

Data Index: 1609950 (Python Code)

Max Activating Token Index: 484

Text #12

Max Range: 0.5911. Min Range: -0.5911

Max Act: 0.5235. Min Act: 0.0000

Data Index: 1545655 (Python Code)

Max Activating Token Index: 478

Text #13

Max Range: 0.5911. Min Range: -0.5911

Max Act: 0.5070. Min Act: 0.0000

Data Index: 1524319 (Python Code)

Max Activating Token Index: 214

Text #14

Max Range: 0.5911. Min Range: -0.5911

Max Act: 0.5106. Min Act: -0.0001

Data Index: 1395852 (Python Code)

Max Activating Token Index: 750

Text #15

Max Range: 0.5911. Min Range: -0.5911

Max Act: 0.5160. Min Act: 0.0000

Data Index: 1620277 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 0.5911. Min Range: -0.5911

Max Act: 0.5163. Min Act: 0.0000

Data Index: 1634511 (Python Code)

Max Activating Token Index: 627

Text #17

Max Range: 0.5911. Min Range: -0.5911

Max Act: 0.5139. Min Act: -0.0000

Data Index: 1564909 (Python Code)

Max Activating Token Index: 737

Text #18

Max Range: 0.5911. Min Range: -0.5911

Max Act: 0.5117. Min Act: 0.0000

Data Index: 1497348 (Python Code)

Max Activating Token Index: 326

Text #19

Max Range: 0.5911. Min Range: -0.5911

Max Act: 0.4871. Min Act: 0.0000

Data Index: 1575822 (Python Code)

Max Activating Token Index: 858