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

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

Neuron 2822 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: 0.2828. Min Range: -0.2828

Max Act: 0.2828. Min Act: -0.0001

Data Index: 1614528 (Python Code)

Max Activating Token Index: 38

Text #1

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2438. Min Act: -0.0001

Data Index: 1519163 (Python Code)

Max Activating Token Index: 835

Text #2

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2594. Min Act: -0.0001

Data Index: 1585955 (Python Code)

Max Activating Token Index: 25

Text #3

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2510. Min Act: -0.0001

Data Index: 1495506 (Python Code)

Max Activating Token Index: 487

Text #4

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2400. Min Act: -0.0001

Data Index: 1642098 (Python Code)

Max Activating Token Index: 927

Text #5

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2467. Min Act: -0.0001

Data Index: 1450206 (Python Code)

Max Activating Token Index: 669

Text #6

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2613. Min Act: -0.0001

Data Index: 1652641 (Python Code)

Max Activating Token Index: 1022

Text #7

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2355. Min Act: -0.0001

Data Index: 1376081 (Python Code)

Max Activating Token Index: 90

Text #8

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2266. Min Act: -0.0001

Data Index: 1626863 (Python Code)

Max Activating Token Index: 154

Text #9

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2086. Min Act: -0.0001

Data Index: 1422251 (Python Code)

Max Activating Token Index: 671

Text #10

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2350. Min Act: -0.0001

Data Index: 1491154 (Python Code)

Max Activating Token Index: 533

Text #11

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2482. Min Act: -0.0001

Data Index: 1394451 (Python Code)

Max Activating Token Index: 319

Text #12

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2265. Min Act: -0.0001

Data Index: 1381894 (Python Code)

Max Activating Token Index: 46

Text #13

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2248. Min Act: -0.0001

Data Index: 1411183 (Python Code)

Max Activating Token Index: 501

Text #14

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2259. Min Act: -0.0001

Data Index: 1616631 (Python Code)

Max Activating Token Index: 242

Text #15

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2102. Min Act: -0.0001

Data Index: 1562044 (Python Code)

Max Activating Token Index: 26

Text #16

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2049. Min Act: -0.0001

Data Index: 1616856 (Python Code)

Max Activating Token Index: 325

Text #17

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2037. Min Act: -0.0001

Data Index: 1414853 (Python Code)

Max Activating Token Index: 116

Text #18

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2151. Min Act: -0.0001

Data Index: 1382465 (Python Code)

Max Activating Token Index: 112

Text #19

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.1997. Min Act: -0.0001

Data Index: 1520352 (Python Code)

Max Activating Token Index: 48