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

Dataset: The Pile

Neuron 554 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: 0.9149. Min Range: -0.9149

Max Act: 0.9050. Min Act: -0.0000

Data Index: 541279 (The Pile)

Max Activating Token Index: 117

Text #1

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.8708. Min Act: -0.0000

Data Index: 1807484 (The Pile)

Max Activating Token Index: 16

Text #2

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.9149. Min Act: -0.0000

Data Index: 1936740 (The Pile)

Max Activating Token Index: 501

Text #3

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.8338. Min Act: -0.0000

Data Index: 1707310 (The Pile)

Max Activating Token Index: 11

Text #4

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1528735 (The Pile)

Max Activating Token Index: 901

Text #5

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.7808. Min Act: -0.0000

Data Index: 1127679 (The Pile)

Max Activating Token Index: 259

Text #6

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.7720. Min Act: -0.0000

Data Index: 1172618 (The Pile)

Max Activating Token Index: 358

Text #7

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.7646. Min Act: -0.0000

Data Index: 1756832 (The Pile)

Max Activating Token Index: 338

Text #8

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.7469. Min Act: -0.0000

Data Index: 1656847 (The Pile)

Max Activating Token Index: 74

Text #9

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6900. Min Act: -0.0000

Data Index: 1896339 (The Pile)

Max Activating Token Index: 254

Text #10

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.7254. Min Act: -0.0000

Data Index: 1290960 (The Pile)

Max Activating Token Index: 409

Text #11

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.7278. Min Act: -0.0000

Data Index: 206323 (The Pile)

Max Activating Token Index: 559

Text #12

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6808. Min Act: -0.0000

Data Index: 681016 (The Pile)

Max Activating Token Index: 699

Text #13

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6642. Min Act: -0.0000

Data Index: 124967 (The Pile)

Max Activating Token Index: 279

Text #14

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6704. Min Act: 0.0000

Data Index: 1101434 (The Pile)

Max Activating Token Index: 436

Text #15

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.7112. Min Act: 0.0000

Data Index: 1180738 (The Pile)

Max Activating Token Index: 339

Text #16

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.7036. Min Act: -0.0000

Data Index: 1906633 (The Pile)

Max Activating Token Index: 6

Text #17

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.7017. Min Act: 0.0000

Data Index: 1646008 (The Pile)

Max Activating Token Index: 243

Text #18

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6451. Min Act: -0.0000

Data Index: 1264199 (The Pile)

Max Activating Token Index: 133

Text #19

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6778. Min Act: -0.0000

Data Index: 1530983 (The Pile)

Max Activating Token Index: 327