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

Dataset: The Pile

Neuron 1372 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.6152. Min Act: -0.0001

Data Index: 1697733 (The Pile)

Max Activating Token Index: 203

Text #1

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.6751. Min Act: -0.0001

Data Index: 1252771 (The Pile)

Max Activating Token Index: 151

Text #2

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5302. Min Act: -0.0000

Data Index: 1264984 (The Pile)

Max Activating Token Index: 108

Text #3

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5774. Min Act: -0.0000

Data Index: 341378 (The Pile)

Max Activating Token Index: 317

Text #4

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5149. Min Act: -0.0000

Data Index: 316950 (The Pile)

Max Activating Token Index: 301

Text #5

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5421. Min Act: -0.0000

Data Index: 619984 (The Pile)

Max Activating Token Index: 886

Text #6

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4724. Min Act: -0.0000

Data Index: 913100 (The Pile)

Max Activating Token Index: 421

Text #7

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5393. Min Act: -0.0000

Data Index: 1730518 (The Pile)

Max Activating Token Index: 214

Text #8

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4859. Min Act: -0.0000

Data Index: 823227 (The Pile)

Max Activating Token Index: 398

Text #9

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4153. Min Act: -0.0000

Data Index: 495331 (The Pile)

Max Activating Token Index: 548

Text #10

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.5775. Min Act: -0.0000

Data Index: 1720414 (The Pile)

Max Activating Token Index: 692

Text #11

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4467. Min Act: -0.0000

Data Index: 450177 (The Pile)

Max Activating Token Index: 892

Text #12

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4749. Min Act: -0.0000

Data Index: 1096525 (The Pile)

Max Activating Token Index: 318

Text #13

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4694. Min Act: -0.0000

Data Index: 748193 (The Pile)

Max Activating Token Index: 822

Text #14

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4631. Min Act: -0.0000

Data Index: 1455448 (The Pile)

Max Activating Token Index: 190

Text #15

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4678. Min Act: -0.0000

Data Index: 569994 (The Pile)

Max Activating Token Index: 378

Text #16

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4596. Min Act: -0.0000

Data Index: 1968227 (The Pile)

Max Activating Token Index: 561

Text #17

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4330. Min Act: -0.0000

Data Index: 540805 (The Pile)

Max Activating Token Index: 439

Text #18

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4077. Min Act: -0.0000

Data Index: 1796051 (The Pile)

Max Activating Token Index: 289

Text #19

Max Range: 0.6751. Min Range: -0.6751

Max Act: 0.4695. Min Act: -0.0000

Data Index: 1562672 (The Pile)

Max Activating Token Index: 955