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

Dataset: The Pile

Neuron 2608 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2316. Min Act: -0.0000

Data Index: 155891 (The Pile)

Max Activating Token Index: 337

Text #1

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2270. Min Act: -0.0000

Data Index: 329126 (The Pile)

Max Activating Token Index: 835

Text #2

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2191. Min Act: -0.0000

Data Index: 1121163 (The Pile)

Max Activating Token Index: 552

Text #3

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2165. Min Act: -0.0000

Data Index: 690940 (The Pile)

Max Activating Token Index: 458

Text #4

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1103249 (The Pile)

Max Activating Token Index: 776

Text #5

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2321. Min Act: -0.0000

Data Index: 1384548 (The Pile)

Max Activating Token Index: 266

Text #6

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1786. Min Act: -0.0000

Data Index: 570997 (The Pile)

Max Activating Token Index: 827

Text #7

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1966. Min Act: -0.0000

Data Index: 184175 (The Pile)

Max Activating Token Index: 593

Text #8

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2043. Min Act: -0.0000

Data Index: 141461 (The Pile)

Max Activating Token Index: 556

Text #9

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2097. Min Act: -0.0000

Data Index: 295448 (The Pile)

Max Activating Token Index: 468

Text #10

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1880. Min Act: -0.0000

Data Index: 33761 (The Pile)

Max Activating Token Index: 470

Text #11

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2219. Min Act: -0.0000

Data Index: 714865 (The Pile)

Max Activating Token Index: 461

Text #12

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1922. Min Act: -0.0000

Data Index: 109005 (The Pile)

Max Activating Token Index: 980

Text #13

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2130. Min Act: -0.0000

Data Index: 718287 (The Pile)

Max Activating Token Index: 626

Text #14

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2207. Min Act: -0.0000

Data Index: 1912160 (The Pile)

Max Activating Token Index: 863

Text #15

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1914. Min Act: -0.0000

Data Index: 1246704 (The Pile)

Max Activating Token Index: 764

Text #16

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1979035 (The Pile)

Max Activating Token Index: 693

Text #17

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2146. Min Act: -0.0000

Data Index: 128243 (The Pile)

Max Activating Token Index: 370

Text #18

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1889385 (The Pile)

Max Activating Token Index: 458

Text #19

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1988. Min Act: -0.0000

Data Index: 1420594 (The Pile)

Max Activating Token Index: 442