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

Dataset: The Pile

Neuron 2525 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: 1.8392. Min Range: -1.8392

Max Act: 1.8392. Min Act: -0.0000

Data Index: 164067 (The Pile)

Max Activating Token Index: 739

Text #1

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.4916. Min Act: -0.0000

Data Index: 636983 (The Pile)

Max Activating Token Index: 297

Text #2

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.4958. Min Act: -0.0000

Data Index: 19294 (The Pile)

Max Activating Token Index: 403

Text #3

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.5164. Min Act: -0.0000

Data Index: 1874659 (The Pile)

Max Activating Token Index: 271

Text #4

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.6336. Min Act: -0.0000

Data Index: 751451 (The Pile)

Max Activating Token Index: 1014

Text #5

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.1540. Min Act: -0.0000

Data Index: 1659227 (The Pile)

Max Activating Token Index: 143

Text #6

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.2399. Min Act: -0.0000

Data Index: 1675481 (The Pile)

Max Activating Token Index: 1012

Text #7

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.2656. Min Act: -0.0000

Data Index: 1856100 (The Pile)

Max Activating Token Index: 977

Text #8

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.3709. Min Act: -0.0000

Data Index: 1544580 (The Pile)

Max Activating Token Index: 229

Text #9

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.0941. Min Act: -0.0000

Data Index: 1448241 (The Pile)

Max Activating Token Index: 525

Text #10

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.5125. Min Act: -0.0000

Data Index: 44616 (The Pile)

Max Activating Token Index: 843

Text #11

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.3303. Min Act: -0.0000

Data Index: 899555 (The Pile)

Max Activating Token Index: 1020

Text #12

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.4386. Min Act: -0.0000

Data Index: 381106 (The Pile)

Max Activating Token Index: 414

Text #13

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.2859. Min Act: -0.0000

Data Index: 1511487 (The Pile)

Max Activating Token Index: 218

Text #14

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.3530. Min Act: -0.0000

Data Index: 1075541 (The Pile)

Max Activating Token Index: 888

Text #15

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.1418. Min Act: -0.0000

Data Index: 205617 (The Pile)

Max Activating Token Index: 230

Text #16

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.3191. Min Act: -0.0000

Data Index: 805306 (The Pile)

Max Activating Token Index: 318

Text #17

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.1872. Min Act: -0.0000

Data Index: 742645 (The Pile)

Max Activating Token Index: 839

Text #18

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.2371. Min Act: -0.0000

Data Index: 1581908 (The Pile)

Max Activating Token Index: 416

Text #19

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.2258. Min Act: -0.0000

Data Index: 578812 (The Pile)

Max Activating Token Index: 270