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

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

Neuron 3453 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2173. Min Range: -1.2173

Max Act: 1.2173. Min Act: -0.0001

Data Index: 1626580 (Python Code)

Max Activating Token Index: 806

Text #1

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.9148. Min Act: -0.0001

Data Index: 1564022 (Python Code)

Max Activating Token Index: 907

Text #2

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.9555. Min Act: -0.0001

Data Index: 1472450 (Python Code)

Max Activating Token Index: 461

Text #3

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.8936. Min Act: -0.0001

Data Index: 1604661 (Python Code)

Max Activating Token Index: 416

Text #4

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.9165. Min Act: -0.0001

Data Index: 1496808 (Python Code)

Max Activating Token Index: 692

Text #5

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.9336. Min Act: -0.0001

Data Index: 1543947 (Python Code)

Max Activating Token Index: 726

Text #6

Max Range: 1.2173. Min Range: -1.2173

Max Act: 1.0323. Min Act: -0.0001

Data Index: 1447190 (Python Code)

Max Activating Token Index: 325

Text #7

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.9195. Min Act: -0.0001

Data Index: 1625994 (Python Code)

Max Activating Token Index: 328

Text #8

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.9155. Min Act: -0.0001

Data Index: 1503222 (Python Code)

Max Activating Token Index: 677

Text #9

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.8782. Min Act: -0.0001

Data Index: 1485093 (Python Code)

Max Activating Token Index: 454

Text #10

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.8368. Min Act: -0.0001

Data Index: 1609105 (Python Code)

Max Activating Token Index: 670

Text #11

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.8603. Min Act: -0.0001

Data Index: 1643894 (Python Code)

Max Activating Token Index: 830

Text #12

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.8597. Min Act: -0.0001

Data Index: 1520036 (Python Code)

Max Activating Token Index: 139

Text #13

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.7647. Min Act: -0.0001

Data Index: 1530465 (Python Code)

Max Activating Token Index: 676

Text #14

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.8116. Min Act: -0.0001

Data Index: 1609179 (Python Code)

Max Activating Token Index: 749

Text #15

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.8588. Min Act: -0.0001

Data Index: 1373459 (Python Code)

Max Activating Token Index: 3

Text #16

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.8301. Min Act: -0.0001

Data Index: 1546375 (Python Code)

Max Activating Token Index: 801

Text #17

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.8290. Min Act: -0.0001

Data Index: 1457693 (Python Code)

Max Activating Token Index: 404

Text #18

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.8538. Min Act: -0.0001

Data Index: 1410051 (Python Code)

Max Activating Token Index: 523

Text #19

Max Range: 1.2173. Min Range: -1.2173

Max Act: 0.8269. Min Act: -0.0001

Data Index: 1552266 (Python Code)

Max Activating Token Index: 896