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

Dataset: The Pile

Neuron 848 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: 0.6645. Min Range: -0.6645

Max Act: 0.6645. Min Act: -0.0000

Data Index: 1104024 (The Pile)

Max Activating Token Index: 449

Text #1

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6194. Min Act: -0.0000

Data Index: 1367508 (The Pile)

Max Activating Token Index: 564

Text #2

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6435. Min Act: -0.0000

Data Index: 278377 (The Pile)

Max Activating Token Index: 183

Text #3

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6231. Min Act: -0.0000

Data Index: 1884082 (The Pile)

Max Activating Token Index: 465

Text #4

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5706. Min Act: -0.0000

Data Index: 944712 (The Pile)

Max Activating Token Index: 404

Text #5

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6265. Min Act: -0.0000

Data Index: 787307 (The Pile)

Max Activating Token Index: 587

Text #6

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5835. Min Act: -0.0000

Data Index: 1891673 (The Pile)

Max Activating Token Index: 361

Text #7

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5505. Min Act: -0.0000

Data Index: 533855 (The Pile)

Max Activating Token Index: 323

Text #8

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1163258 (The Pile)

Max Activating Token Index: 222

Text #9

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5818. Min Act: -0.0000

Data Index: 371957 (The Pile)

Max Activating Token Index: 385

Text #10

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5759. Min Act: -0.0000

Data Index: 1163102 (The Pile)

Max Activating Token Index: 587

Text #11

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5162. Min Act: -0.0000

Data Index: 1014783 (The Pile)

Max Activating Token Index: 919

Text #12

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5118. Min Act: -0.0000

Data Index: 359832 (The Pile)

Max Activating Token Index: 450

Text #13

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4776. Min Act: -0.0000

Data Index: 994987 (The Pile)

Max Activating Token Index: 237

Text #14

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5129. Min Act: -0.0000

Data Index: 1104531 (The Pile)

Max Activating Token Index: 679

Text #15

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4982. Min Act: -0.0000

Data Index: 1193466 (The Pile)

Max Activating Token Index: 818

Text #16

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5159. Min Act: -0.0000

Data Index: 745766 (The Pile)

Max Activating Token Index: 930

Text #17

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5296. Min Act: -0.0000

Data Index: 1004891 (The Pile)

Max Activating Token Index: 283

Text #18

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5104. Min Act: -0.0000

Data Index: 48988 (The Pile)

Max Activating Token Index: 362

Text #19

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1623635 (The Pile)

Max Activating Token Index: 308