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

Dataset: The Pile

Neuron 3474 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0796. Min Range: -1.0796

Max Act: 1.0185. Min Act: -0.0000

Data Index: 217434 (The Pile)

Max Activating Token Index: 290

Text #1

Max Range: 1.0796. Min Range: -1.0796

Max Act: 1.0694. Min Act: -0.0000

Data Index: 1067953 (The Pile)

Max Activating Token Index: 336

Text #2

Max Range: 1.0796. Min Range: -1.0796

Max Act: 1.0754. Min Act: -0.0000

Data Index: 1348350 (The Pile)

Max Activating Token Index: 367

Text #3

Max Range: 1.0796. Min Range: -1.0796

Max Act: 1.0796. Min Act: -0.0000

Data Index: 64723 (The Pile)

Max Activating Token Index: 315

Text #4

Max Range: 1.0796. Min Range: -1.0796

Max Act: 0.9793. Min Act: -0.0000

Data Index: 725221 (The Pile)

Max Activating Token Index: 374

Text #5

Max Range: 1.0796. Min Range: -1.0796

Max Act: 0.9618. Min Act: -0.0000

Data Index: 499045 (The Pile)

Max Activating Token Index: 557

Text #6

Max Range: 1.0796. Min Range: -1.0796

Max Act: 1.0388. Min Act: -0.0000

Data Index: 1188015 (The Pile)

Max Activating Token Index: 396

Text #7

Max Range: 1.0796. Min Range: -1.0796

Max Act: 1.0446. Min Act: -0.0000

Data Index: 185471 (The Pile)

Max Activating Token Index: 431

Text #8

Max Range: 1.0796. Min Range: -1.0796

Max Act: 0.9022. Min Act: -0.0000

Data Index: 996521 (The Pile)

Max Activating Token Index: 479

Text #9

Max Range: 1.0796. Min Range: -1.0796

Max Act: 0.8692. Min Act: -0.0000

Data Index: 1693377 (The Pile)

Max Activating Token Index: 145

Text #10

Max Range: 1.0796. Min Range: -1.0796

Max Act: 0.9511. Min Act: -0.0000

Data Index: 901284 (The Pile)

Max Activating Token Index: 650

Text #11

Max Range: 1.0796. Min Range: -1.0796

Max Act: 0.8346. Min Act: -0.0000

Data Index: 1068191 (The Pile)

Max Activating Token Index: 144

Text #12

Max Range: 1.0796. Min Range: -1.0796

Max Act: 0.9638. Min Act: -0.0000

Data Index: 21844 (The Pile)

Max Activating Token Index: 287

Text #13

Max Range: 1.0796. Min Range: -1.0796

Max Act: 0.9314. Min Act: -0.0000

Data Index: 639812 (The Pile)

Max Activating Token Index: 220

Text #14

Max Range: 1.0796. Min Range: -1.0796

Max Act: 0.8692. Min Act: -0.0000

Data Index: 336337 (The Pile)

Max Activating Token Index: 237

Text #15

Max Range: 1.0796. Min Range: -1.0796

Max Act: 0.9801. Min Act: -0.0000

Data Index: 1545572 (The Pile)

Max Activating Token Index: 809

Text #16

Max Range: 1.0796. Min Range: -1.0796

Max Act: 0.9428. Min Act: -0.0000

Data Index: 1957637 (The Pile)

Max Activating Token Index: 369

Text #17

Max Range: 1.0796. Min Range: -1.0796

Max Act: 0.8935. Min Act: -0.0000

Data Index: 1746665 (The Pile)

Max Activating Token Index: 889

Text #18

Max Range: 1.0796. Min Range: -1.0796

Max Act: 0.8650. Min Act: -0.0000

Data Index: 1017890 (The Pile)

Max Activating Token Index: 201

Text #19

Max Range: 1.0796. Min Range: -1.0796

Max Act: 0.9287. Min Act: -0.0000

Data Index: 702871 (The Pile)

Max Activating Token Index: 230