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

Dataset: The Pile

Neuron 3348 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: 1.0241. Min Range: -1.0241

Max Act: 1.0241. Min Act: -0.0000

Data Index: 2289 (The Pile)

Max Activating Token Index: 512

Text #1

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8509. Min Act: -0.0000

Data Index: 1255898 (The Pile)

Max Activating Token Index: 174

Text #2

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8854. Min Act: -0.0000

Data Index: 476384 (The Pile)

Max Activating Token Index: 796

Text #3

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8628. Min Act: -0.0000

Data Index: 791108 (The Pile)

Max Activating Token Index: 827

Text #4

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8681. Min Act: -0.0000

Data Index: 1797929 (The Pile)

Max Activating Token Index: 474

Text #5

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8440. Min Act: -0.0000

Data Index: 1407024 (The Pile)

Max Activating Token Index: 974

Text #6

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8902. Min Act: -0.0000

Data Index: 645351 (The Pile)

Max Activating Token Index: 614

Text #7

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8801. Min Act: -0.0000

Data Index: 360997 (The Pile)

Max Activating Token Index: 257

Text #8

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8536. Min Act: -0.0000

Data Index: 1249438 (The Pile)

Max Activating Token Index: 551

Text #9

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8905. Min Act: -0.0000

Data Index: 1159435 (The Pile)

Max Activating Token Index: 194

Text #10

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8541. Min Act: -0.0000

Data Index: 771457 (The Pile)

Max Activating Token Index: 782

Text #11

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8265. Min Act: -0.0000

Data Index: 996364 (The Pile)

Max Activating Token Index: 315

Text #12

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8006. Min Act: -0.0000

Data Index: 1848466 (The Pile)

Max Activating Token Index: 395

Text #13

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1401848 (The Pile)

Max Activating Token Index: 29

Text #14

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7564. Min Act: -0.0000

Data Index: 875330 (The Pile)

Max Activating Token Index: 881

Text #15

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8077. Min Act: -0.0000

Data Index: 1722263 (The Pile)

Max Activating Token Index: 427

Text #16

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8036. Min Act: -0.0000

Data Index: 1231769 (The Pile)

Max Activating Token Index: 396

Text #17

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8040. Min Act: -0.0000

Data Index: 853381 (The Pile)

Max Activating Token Index: 835

Text #18

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8242. Min Act: -0.0000

Data Index: 114872 (The Pile)

Max Activating Token Index: 989

Text #19

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8158. Min Act: -0.0000

Data Index: 341814 (The Pile)

Max Activating Token Index: 675