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

Dataset: The Pile

Neuron 994 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: 3.1357. Min Range: -3.1357

Max Act: 3.1357. Min Act: -0.0000

Data Index: 908155 (The Pile)

Max Activating Token Index: 149

Text #1

Max Range: 3.1357. Min Range: -3.1357

Max Act: 3.0815. Min Act: -0.0000

Data Index: 1733062 (The Pile)

Max Activating Token Index: 300

Text #2

Max Range: 3.1357. Min Range: -3.1357

Max Act: 2.7968. Min Act: -0.0000

Data Index: 378978 (The Pile)

Max Activating Token Index: 374

Text #3

Max Range: 3.1357. Min Range: -3.1357

Max Act: 2.8359. Min Act: -0.0000

Data Index: 1462017 (The Pile)

Max Activating Token Index: 465

Text #4

Max Range: 3.1357. Min Range: -3.1357

Max Act: 2.6845. Min Act: -0.0000

Data Index: 1548816 (The Pile)

Max Activating Token Index: 130

Text #5

Max Range: 3.1357. Min Range: -3.1357

Max Act: 2.7222. Min Act: -0.0000

Data Index: 1634277 (The Pile)

Max Activating Token Index: 380

Text #6

Max Range: 3.1357. Min Range: -3.1357

Max Act: 2.3857. Min Act: -0.0000

Data Index: 1388147 (The Pile)

Max Activating Token Index: 132

Text #7

Max Range: 3.1357. Min Range: -3.1357

Max Act: 2.4865. Min Act: -0.0000

Data Index: 458651 (The Pile)

Max Activating Token Index: 619

Text #8

Max Range: 3.1357. Min Range: -3.1357

Max Act: 2.4251. Min Act: -0.0000

Data Index: 1000637 (The Pile)

Max Activating Token Index: 62

Text #9

Max Range: 3.1357. Min Range: -3.1357

Max Act: 2.4101. Min Act: -0.0000

Data Index: 1392125 (The Pile)

Max Activating Token Index: 144

Text #10

Max Range: 3.1357. Min Range: -3.1357

Max Act: 2.3979. Min Act: -0.0000

Data Index: 1108822 (The Pile)

Max Activating Token Index: 541

Text #11

Max Range: 3.1357. Min Range: -3.1357

Max Act: 2.2773. Min Act: -0.0000

Data Index: 1158366 (The Pile)

Max Activating Token Index: 138

Text #12

Max Range: 3.1357. Min Range: -3.1357

Max Act: 2.4971. Min Act: -0.0000

Data Index: 927913 (The Pile)

Max Activating Token Index: 17

Text #13

Max Range: 3.1357. Min Range: -3.1357

Max Act: 2.5016. Min Act: 0.0000

Data Index: 1031881 (The Pile)

Max Activating Token Index: 278

Text #14

Max Range: 3.1357. Min Range: -3.1357

Max Act: 2.5112. Min Act: -0.0000

Data Index: 415038 (The Pile)

Max Activating Token Index: 62

Text #15

Max Range: 3.1357. Min Range: -3.1357

Max Act: 2.3532. Min Act: -0.0000

Data Index: 878496 (The Pile)

Max Activating Token Index: 392

Text #16

Max Range: 3.1357. Min Range: -3.1357

Max Act: 2.3334. Min Act: -0.0000

Data Index: 66287 (The Pile)

Max Activating Token Index: 934

Text #17

Max Range: 3.1357. Min Range: -3.1357

Max Act: 2.3174. Min Act: -0.0000

Data Index: 964790 (The Pile)

Max Activating Token Index: 967

Text #18

Max Range: 3.1357. Min Range: -3.1357

Max Act: 2.3253. Min Act: -0.0000

Data Index: 1080289 (The Pile)

Max Activating Token Index: 923

Text #19

Max Range: 3.1357. Min Range: -3.1357

Max Act: 2.4355. Min Act: -0.0000

Data Index: 1176479 (The Pile)

Max Activating Token Index: 854