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

Dataset: The Pile

Neuron 4812 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.8210. Min Act: -0.0000

Data Index: 1327188 (The Pile)

Max Activating Token Index: 399

Text #1

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.8411. Min Act: -0.0000

Data Index: 1921735 (The Pile)

Max Activating Token Index: 820

Text #2

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.7236. Min Act: -0.0000

Data Index: 398962 (The Pile)

Max Activating Token Index: 56

Text #3

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.7656. Min Act: -0.0000

Data Index: 840734 (The Pile)

Max Activating Token Index: 917

Text #4

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.7425. Min Act: -0.0000

Data Index: 444214 (The Pile)

Max Activating Token Index: 902

Text #5

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.7873. Min Act: -0.0000

Data Index: 529952 (The Pile)

Max Activating Token Index: 501

Text #6

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.7065. Min Act: -0.0000

Data Index: 597354 (The Pile)

Max Activating Token Index: 222

Text #7

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6770. Min Act: -0.0000

Data Index: 1155848 (The Pile)

Max Activating Token Index: 666

Text #8

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6751. Min Act: 0.0000

Data Index: 701903 (The Pile)

Max Activating Token Index: 70

Text #9

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6712. Min Act: -0.0000

Data Index: 356234 (The Pile)

Max Activating Token Index: 928

Text #10

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6241. Min Act: -0.0000

Data Index: 385904 (The Pile)

Max Activating Token Index: 346

Text #11

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6185. Min Act: -0.0000

Data Index: 265481 (The Pile)

Max Activating Token Index: 929

Text #12

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6302. Min Act: -0.0000

Data Index: 1214285 (The Pile)

Max Activating Token Index: 486

Text #13

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1144145 (The Pile)

Max Activating Token Index: 296

Text #14

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.6591. Min Act: -0.0000

Data Index: 473560 (The Pile)

Max Activating Token Index: 138

Text #15

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5806. Min Act: -0.0000

Data Index: 1477425 (The Pile)

Max Activating Token Index: 225

Text #16

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5974. Min Act: -0.0000

Data Index: 326648 (The Pile)

Max Activating Token Index: 62

Text #17

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5846. Min Act: -0.0000

Data Index: 669104 (The Pile)

Max Activating Token Index: 322

Text #18

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1285796 (The Pile)

Max Activating Token Index: 378

Text #19

Max Range: 0.8411. Min Range: -0.8411

Max Act: 0.5624. Min Act: 0.0000

Data Index: 1637066 (The Pile)

Max Activating Token Index: 670