Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1438 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.4298. Min Act: -0.0000

Data Index: 451867 (The Pile)

Max Activating Token Index: 551

Text #1

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.4119. Min Act: 0.0000

Data Index: 331754 (The Pile)

Max Activating Token Index: 671

Text #2

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3510. Min Act: -0.0000

Data Index: 614985 (The Pile)

Max Activating Token Index: 201

Text #3

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3533. Min Act: -0.0000

Data Index: 1461755 (The Pile)

Max Activating Token Index: 653

Text #4

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3848. Min Act: -0.0000

Data Index: 1329413 (The Pile)

Max Activating Token Index: 433

Text #5

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1940755 (The Pile)

Max Activating Token Index: 700

Text #6

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3651. Min Act: -0.0000

Data Index: 340005 (The Pile)

Max Activating Token Index: 32

Text #7

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3643. Min Act: -0.0000

Data Index: 1796482 (The Pile)

Max Activating Token Index: 1012

Text #8

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3583. Min Act: 0.0000

Data Index: 532177 (The Pile)

Max Activating Token Index: 40

Text #9

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1345999 (The Pile)

Max Activating Token Index: 370

Text #10

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3383. Min Act: -0.0000

Data Index: 429081 (The Pile)

Max Activating Token Index: 532

Text #11

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3356. Min Act: -0.0000

Data Index: 1599019 (The Pile)

Max Activating Token Index: 244

Text #12

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.2988. Min Act: -0.0000

Data Index: 386905 (The Pile)

Max Activating Token Index: 295

Text #13

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3277. Min Act: -0.0000

Data Index: 1463918 (The Pile)

Max Activating Token Index: 269

Text #14

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3062. Min Act: -0.0000

Data Index: 149907 (The Pile)

Max Activating Token Index: 538

Text #15

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3065. Min Act: -0.0000

Data Index: 983970 (The Pile)

Max Activating Token Index: 597

Text #16

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.2705. Min Act: -0.0000

Data Index: 1912115 (The Pile)

Max Activating Token Index: 967

Text #17

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3309. Min Act: -0.0000

Data Index: 632556 (The Pile)

Max Activating Token Index: 30

Text #18

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3096. Min Act: -0.0000

Data Index: 184302 (The Pile)

Max Activating Token Index: 111

Text #19

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3051. Min Act: -0.0000

Data Index: 1556670 (The Pile)

Max Activating Token Index: 206