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

Dataset: The Pile

Neuron 1326 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: 0.9550. Min Range: -0.9550

Max Act: 0.9110. Min Act: -0.0000

Data Index: 599302 (The Pile)

Max Activating Token Index: 234

Text #1

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.9550. Min Act: -0.0000

Data Index: 935598 (The Pile)

Max Activating Token Index: 272

Text #2

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.8084. Min Act: -0.0000

Data Index: 1750928 (The Pile)

Max Activating Token Index: 636

Text #3

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7986. Min Act: -0.0000

Data Index: 606615 (The Pile)

Max Activating Token Index: 823

Text #4

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.8862. Min Act: -0.0000

Data Index: 197677 (The Pile)

Max Activating Token Index: 309

Text #5

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.8488. Min Act: -0.0000

Data Index: 1939235 (The Pile)

Max Activating Token Index: 143

Text #6

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7521. Min Act: -0.0000

Data Index: 770006 (The Pile)

Max Activating Token Index: 616

Text #7

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.8315. Min Act: -0.0000

Data Index: 884026 (The Pile)

Max Activating Token Index: 284

Text #8

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7928. Min Act: -0.0000

Data Index: 1653356 (The Pile)

Max Activating Token Index: 294

Text #9

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.8346. Min Act: -0.0000

Data Index: 1515852 (The Pile)

Max Activating Token Index: 285

Text #10

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.6581. Min Act: -0.0000

Data Index: 427241 (The Pile)

Max Activating Token Index: 975

Text #11

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.8139. Min Act: -0.0000

Data Index: 1795606 (The Pile)

Max Activating Token Index: 101

Text #12

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7892. Min Act: -0.0000

Data Index: 314115 (The Pile)

Max Activating Token Index: 192

Text #13

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.8040. Min Act: -0.0000

Data Index: 1648669 (The Pile)

Max Activating Token Index: 564

Text #14

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.8506. Min Act: -0.0000

Data Index: 316995 (The Pile)

Max Activating Token Index: 498

Text #15

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.8176. Min Act: -0.0000

Data Index: 1995596 (The Pile)

Max Activating Token Index: 620

Text #16

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1410894 (The Pile)

Max Activating Token Index: 358

Text #17

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1814373 (The Pile)

Max Activating Token Index: 762

Text #18

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.8104. Min Act: -0.0000

Data Index: 1249706 (The Pile)

Max Activating Token Index: 752

Text #19

Max Range: 0.9550. Min Range: -0.9550

Max Act: 0.7001. Min Act: -0.0000

Data Index: 347560 (The Pile)

Max Activating Token Index: 354