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

Dataset: The Pile

Neuron 921 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.5321. Min Act: -0.0000

Data Index: 981334 (The Pile)

Max Activating Token Index: 646

Text #1

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1418109 (The Pile)

Max Activating Token Index: 524

Text #2

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.5355. Min Act: -0.0000

Data Index: 215012 (The Pile)

Max Activating Token Index: 197

Text #3

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4437. Min Act: -0.0000

Data Index: 888349 (The Pile)

Max Activating Token Index: 712

Text #4

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4891. Min Act: -0.0000

Data Index: 341443 (The Pile)

Max Activating Token Index: 636

Text #5

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4248. Min Act: -0.0000

Data Index: 1678481 (The Pile)

Max Activating Token Index: 808

Text #6

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4192. Min Act: -0.0000

Data Index: 297518 (The Pile)

Max Activating Token Index: 514

Text #7

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4452. Min Act: -0.0000

Data Index: 186284 (The Pile)

Max Activating Token Index: 325

Text #8

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4119. Min Act: -0.0000

Data Index: 1130613 (The Pile)

Max Activating Token Index: 655

Text #9

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.3455. Min Act: -0.0000

Data Index: 1318615 (The Pile)

Max Activating Token Index: 636

Text #10

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.3886. Min Act: -0.0000

Data Index: 1957972 (The Pile)

Max Activating Token Index: 395

Text #11

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4243. Min Act: -0.0000

Data Index: 1897803 (The Pile)

Max Activating Token Index: 412

Text #12

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4046. Min Act: -0.0000

Data Index: 846730 (The Pile)

Max Activating Token Index: 564

Text #13

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4295. Min Act: -0.0000

Data Index: 479907 (The Pile)

Max Activating Token Index: 456

Text #14

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.3682. Min Act: -0.0000

Data Index: 1809266 (The Pile)

Max Activating Token Index: 888

Text #15

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.4278. Min Act: -0.0000

Data Index: 1487464 (The Pile)

Max Activating Token Index: 205

Text #16

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.3922. Min Act: -0.0000

Data Index: 483712 (The Pile)

Max Activating Token Index: 919

Text #17

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.3469. Min Act: -0.0000

Data Index: 1846395 (The Pile)

Max Activating Token Index: 174

Text #18

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.3990. Min Act: -0.0000

Data Index: 1940317 (The Pile)

Max Activating Token Index: 884

Text #19

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.3659. Min Act: -0.0000

Data Index: 1577037 (The Pile)

Max Activating Token Index: 408