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

Dataset: The Pile

Neuron 2259 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: 1.0772. Min Range: -1.0772

Max Act: 1.0772. Min Act: -0.0000

Data Index: 742007 (The Pile)

Max Activating Token Index: 368

Text #1

Max Range: 1.0772. Min Range: -1.0772

Max Act: 0.9995. Min Act: -0.0000

Data Index: 1883415 (The Pile)

Max Activating Token Index: 19

Text #2

Max Range: 1.0772. Min Range: -1.0772

Max Act: 1.0118. Min Act: 0.0000

Data Index: 1640888 (The Pile)

Max Activating Token Index: 42

Text #3

Max Range: 1.0772. Min Range: -1.0772

Max Act: 0.9293. Min Act: -0.0000

Data Index: 1531717 (The Pile)

Max Activating Token Index: 207

Text #4

Max Range: 1.0772. Min Range: -1.0772

Max Act: 0.9218. Min Act: -0.0000

Data Index: 411118 (The Pile)

Max Activating Token Index: 27

Text #5

Max Range: 1.0772. Min Range: -1.0772

Max Act: 0.8867. Min Act: -0.0000

Data Index: 1190924 (The Pile)

Max Activating Token Index: 61

Text #6

Max Range: 1.0772. Min Range: -1.0772

Max Act: 0.9328. Min Act: -0.0000

Data Index: 404196 (The Pile)

Max Activating Token Index: 815

Text #7

Max Range: 1.0772. Min Range: -1.0772

Max Act: 0.8665. Min Act: -0.0000

Data Index: 1694774 (The Pile)

Max Activating Token Index: 465

Text #8

Max Range: 1.0772. Min Range: -1.0772

Max Act: 0.8023. Min Act: -0.0000

Data Index: 695512 (The Pile)

Max Activating Token Index: 436

Text #9

Max Range: 1.0772. Min Range: -1.0772

Max Act: 0.8402. Min Act: -0.0000

Data Index: 483745 (The Pile)

Max Activating Token Index: 676

Text #10

Max Range: 1.0772. Min Range: -1.0772

Max Act: 0.7771. Min Act: -0.0000

Data Index: 1853652 (The Pile)

Max Activating Token Index: 204

Text #11

Max Range: 1.0772. Min Range: -1.0772

Max Act: 0.7417. Min Act: -0.0000

Data Index: 957341 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 1.0772. Min Range: -1.0772

Max Act: 0.7639. Min Act: -0.0000

Data Index: 1863162 (The Pile)

Max Activating Token Index: 798

Text #13

Max Range: 1.0772. Min Range: -1.0772

Max Act: 0.7775. Min Act: -0.0000

Data Index: 492664 (The Pile)

Max Activating Token Index: 572

Text #14

Max Range: 1.0772. Min Range: -1.0772

Max Act: 0.7530. Min Act: -0.0000

Data Index: 178663 (The Pile)

Max Activating Token Index: 951

Text #15

Max Range: 1.0772. Min Range: -1.0772

Max Act: 0.7442. Min Act: 0.0000

Data Index: 43648 (The Pile)

Max Activating Token Index: 848

Text #16

Max Range: 1.0772. Min Range: -1.0772

Max Act: 0.7235. Min Act: -0.0000

Data Index: 1996181 (The Pile)

Max Activating Token Index: 674

Text #17

Max Range: 1.0772. Min Range: -1.0772

Max Act: 0.7606. Min Act: -0.0000

Data Index: 402199 (The Pile)

Max Activating Token Index: 416

Text #18

Max Range: 1.0772. Min Range: -1.0772

Max Act: 0.7116. Min Act: -0.0000

Data Index: 708441 (The Pile)

Max Activating Token Index: 836

Text #19

Max Range: 1.0772. Min Range: -1.0772

Max Act: 0.7297. Min Act: -0.0000

Data Index: 792396 (The Pile)

Max Activating Token Index: 829