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

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

Neuron 1266 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: 0.3048. Min Range: -0.3048

Max Act: 0.3048. Min Act: -0.0001

Data Index: 779223 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2522. Min Act: -0.0001

Data Index: 601480 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2475. Min Act: -0.0001

Data Index: 823982 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2351. Min Act: -0.0001

Data Index: 456516 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2099. Min Act: -0.0001

Data Index: 1311261 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2056. Min Act: -0.0001

Data Index: 1314445 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2187. Min Act: -0.0001

Data Index: 343876 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2259. Min Act: -0.0001

Data Index: 1096979 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2221. Min Act: -0.0001

Data Index: 899530 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2127. Min Act: -0.0001

Data Index: 1262436 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.2030. Min Act: -0.0001

Data Index: 438101 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1985. Min Act: -0.0001

Data Index: 545592 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1899. Min Act: -0.0001

Data Index: 337617 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1952. Min Act: -0.0000

Data Index: 1261864 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1987. Min Act: -0.0001

Data Index: 1239402 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1753. Min Act: -0.0001

Data Index: 396724 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1795. Min Act: -0.0001

Data Index: 1220548 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1670. Min Act: -0.0001

Data Index: 89898 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1725. Min Act: -0.0001

Data Index: 1248241 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1560. Min Act: -0.0001

Data Index: 922679 (C4 (Web Text))

Max Activating Token Index: 173