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

Dataset: The Pile

Neuron 4066 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: 1.4360. Min Range: -1.4360

Max Act: 1.4251. Min Act: -0.0000

Data Index: 574577 (The Pile)

Max Activating Token Index: 410

Text #1

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.4360. Min Act: -0.0000

Data Index: 1707243 (The Pile)

Max Activating Token Index: 575

Text #2

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.2960. Min Act: -0.0000

Data Index: 1201206 (The Pile)

Max Activating Token Index: 379

Text #3

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.2394. Min Act: -0.0001

Data Index: 1216797 (The Pile)

Max Activating Token Index: 272

Text #4

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.2209. Min Act: -0.0000

Data Index: 281083 (The Pile)

Max Activating Token Index: 546

Text #5

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.3317. Min Act: -0.0000

Data Index: 1507353 (The Pile)

Max Activating Token Index: 557

Text #6

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.1936. Min Act: -0.0000

Data Index: 8351 (The Pile)

Max Activating Token Index: 363

Text #7

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.1431. Min Act: -0.0000

Data Index: 552313 (The Pile)

Max Activating Token Index: 371

Text #8

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.1700. Min Act: -0.0000

Data Index: 85868 (The Pile)

Max Activating Token Index: 476

Text #9

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.1494. Min Act: -0.0000

Data Index: 1502384 (The Pile)

Max Activating Token Index: 369

Text #10

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.1016. Min Act: -0.0000

Data Index: 1228033 (The Pile)

Max Activating Token Index: 62

Text #11

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.1724. Min Act: -0.0000

Data Index: 1929515 (The Pile)

Max Activating Token Index: 745

Text #12

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.1016. Min Act: -0.0000

Data Index: 396701 (The Pile)

Max Activating Token Index: 86

Text #13

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.0283. Min Act: -0.0000

Data Index: 1888546 (The Pile)

Max Activating Token Index: 940

Text #14

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.0208. Min Act: -0.0000

Data Index: 1346539 (The Pile)

Max Activating Token Index: 262

Text #15

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.0748. Min Act: -0.0000

Data Index: 1493388 (The Pile)

Max Activating Token Index: 402

Text #16

Max Range: 1.4360. Min Range: -1.4360

Max Act: 0.9417. Min Act: -0.0000

Data Index: 854562 (The Pile)

Max Activating Token Index: 871

Text #17

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.1285. Min Act: -0.0000

Data Index: 951288 (The Pile)

Max Activating Token Index: 460

Text #18

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.0559. Min Act: -0.0000

Data Index: 1992548 (The Pile)

Max Activating Token Index: 907

Text #19

Max Range: 1.4360. Min Range: -1.4360

Max Act: 1.0090. Min Act: -0.0000

Data Index: 1380298 (The Pile)

Max Activating Token Index: 965