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

Dataset: The Pile

Neuron 3419 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.7037. Min Act: -0.0000

Data Index: 182114 (The Pile)

Max Activating Token Index: 695

Text #1

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5646. Min Act: -0.0000

Data Index: 64292 (The Pile)

Max Activating Token Index: 428

Text #2

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5221. Min Act: -0.0000

Data Index: 117102 (The Pile)

Max Activating Token Index: 54

Text #3

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1692609 (The Pile)

Max Activating Token Index: 146

Text #4

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4987. Min Act: -0.0000

Data Index: 382655 (The Pile)

Max Activating Token Index: 288

Text #5

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5131. Min Act: -0.0000

Data Index: 1110777 (The Pile)

Max Activating Token Index: 65

Text #6

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4676. Min Act: -0.0000

Data Index: 611222 (The Pile)

Max Activating Token Index: 299

Text #7

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4796. Min Act: -0.0000

Data Index: 826602 (The Pile)

Max Activating Token Index: 535

Text #8

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5062. Min Act: -0.0000

Data Index: 82357 (The Pile)

Max Activating Token Index: 472

Text #9

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4838. Min Act: -0.0000

Data Index: 401346 (The Pile)

Max Activating Token Index: 241

Text #10

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4610. Min Act: -0.0000

Data Index: 667051 (The Pile)

Max Activating Token Index: 478

Text #11

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4728. Min Act: -0.0000

Data Index: 1613065 (The Pile)

Max Activating Token Index: 616

Text #12

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1504147 (The Pile)

Max Activating Token Index: 933

Text #13

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4541. Min Act: -0.0000

Data Index: 206205 (The Pile)

Max Activating Token Index: 832

Text #14

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1358900 (The Pile)

Max Activating Token Index: 899

Text #15

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5032. Min Act: -0.0000

Data Index: 692142 (The Pile)

Max Activating Token Index: 177

Text #16

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4998. Min Act: -0.0000

Data Index: 479637 (The Pile)

Max Activating Token Index: 413

Text #17

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4866. Min Act: -0.0000

Data Index: 1663322 (The Pile)

Max Activating Token Index: 924

Text #18

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4467. Min Act: -0.0000

Data Index: 394773 (The Pile)

Max Activating Token Index: 631

Text #19

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1694984 (The Pile)

Max Activating Token Index: 353