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

Dataset: The Pile

Neuron 4422 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4623. Min Range: -3.4623

Max Act: 3.3107. Min Act: -0.0000

Data Index: 1577676 (The Pile)

Max Activating Token Index: 1010

Text #1

Max Range: 3.4623. Min Range: -3.4623

Max Act: 3.2013. Min Act: -0.0000

Data Index: 1005608 (The Pile)

Max Activating Token Index: 410

Text #2

Max Range: 3.4623. Min Range: -3.4623

Max Act: 3.4623. Min Act: -0.0000

Data Index: 1172171 (The Pile)

Max Activating Token Index: 1001

Text #3

Max Range: 3.4623. Min Range: -3.4623

Max Act: 3.1629. Min Act: -0.0000

Data Index: 1452864 (The Pile)

Max Activating Token Index: 362

Text #4

Max Range: 3.4623. Min Range: -3.4623

Max Act: 3.2831. Min Act: -0.0000

Data Index: 1009896 (The Pile)

Max Activating Token Index: 489

Text #5

Max Range: 3.4623. Min Range: -3.4623

Max Act: 3.0933. Min Act: -0.0000

Data Index: 1436216 (The Pile)

Max Activating Token Index: 403

Text #6

Max Range: 3.4623. Min Range: -3.4623

Max Act: 3.0860. Min Act: -0.0000

Data Index: 337247 (The Pile)

Max Activating Token Index: 630

Text #7

Max Range: 3.4623. Min Range: -3.4623

Max Act: 3.1509. Min Act: -0.0000

Data Index: 1765022 (The Pile)

Max Activating Token Index: 166

Text #8

Max Range: 3.4623. Min Range: -3.4623

Max Act: 2.8720. Min Act: -0.0001

Data Index: 652338 (The Pile)

Max Activating Token Index: 140

Text #9

Max Range: 3.4623. Min Range: -3.4623

Max Act: 2.6319. Min Act: -0.0000

Data Index: 1268126 (The Pile)

Max Activating Token Index: 315

Text #10

Max Range: 3.4623. Min Range: -3.4623

Max Act: 2.7167. Min Act: -0.0000

Data Index: 814878 (The Pile)

Max Activating Token Index: 454

Text #11

Max Range: 3.4623. Min Range: -3.4623

Max Act: 2.8207. Min Act: -0.0000

Data Index: 469741 (The Pile)

Max Activating Token Index: 21

Text #12

Max Range: 3.4623. Min Range: -3.4623

Max Act: 2.6468. Min Act: -0.0000

Data Index: 62474 (The Pile)

Max Activating Token Index: 573

Text #13

Max Range: 3.4623. Min Range: -3.4623

Max Act: 2.6698. Min Act: -0.0000

Data Index: 532891 (The Pile)

Max Activating Token Index: 328

Text #14

Max Range: 3.4623. Min Range: -3.4623

Max Act: 2.6593. Min Act: -0.0000

Data Index: 51144 (The Pile)

Max Activating Token Index: 1003

Text #15

Max Range: 3.4623. Min Range: -3.4623

Max Act: 2.7571. Min Act: -0.0000

Data Index: 495820 (The Pile)

Max Activating Token Index: 436

Text #16

Max Range: 3.4623. Min Range: -3.4623

Max Act: 2.5979. Min Act: -0.0000

Data Index: 1707054 (The Pile)

Max Activating Token Index: 929

Text #17

Max Range: 3.4623. Min Range: -3.4623

Max Act: 2.6241. Min Act: -0.0000

Data Index: 1424880 (The Pile)

Max Activating Token Index: 425

Text #18

Max Range: 3.4623. Min Range: -3.4623

Max Act: 2.4056. Min Act: -0.0000

Data Index: 1248020 (The Pile)

Max Activating Token Index: 846

Text #19

Max Range: 3.4623. Min Range: -3.4623

Max Act: 2.6168. Min Act: -0.0000

Data Index: 1830517 (The Pile)

Max Activating Token Index: 758