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

Dataset: The Pile

Neuron 1292 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3928. Min Act: -0.0000

Data Index: 597033 (The Pile)

Max Activating Token Index: 292

Text #1

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4671. Min Act: -0.0000

Data Index: 134593 (The Pile)

Max Activating Token Index: 662

Text #2

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4340. Min Act: -0.0000

Data Index: 725557 (The Pile)

Max Activating Token Index: 907

Text #3

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4772. Min Act: -0.0000

Data Index: 866458 (The Pile)

Max Activating Token Index: 995

Text #4

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4210. Min Act: -0.0000

Data Index: 213205 (The Pile)

Max Activating Token Index: 445

Text #5

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4203. Min Act: -0.0000

Data Index: 722750 (The Pile)

Max Activating Token Index: 841

Text #6

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4847. Min Act: -0.0000

Data Index: 1696274 (The Pile)

Max Activating Token Index: 286

Text #7

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1965354 (The Pile)

Max Activating Token Index: 440

Text #8

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4243. Min Act: -0.0000

Data Index: 1746621 (The Pile)

Max Activating Token Index: 695

Text #9

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4027. Min Act: -0.0000

Data Index: 460245 (The Pile)

Max Activating Token Index: 825

Text #10

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4528. Min Act: -0.0000

Data Index: 1742301 (The Pile)

Max Activating Token Index: 527

Text #11

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4229. Min Act: -0.0000

Data Index: 1595427 (The Pile)

Max Activating Token Index: 119

Text #12

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4279. Min Act: -0.0000

Data Index: 1967714 (The Pile)

Max Activating Token Index: 629

Text #13

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4234. Min Act: -0.0000

Data Index: 1082394 (The Pile)

Max Activating Token Index: 695

Text #14

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1228450 (The Pile)

Max Activating Token Index: 513

Text #15

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4075. Min Act: -0.0000

Data Index: 691758 (The Pile)

Max Activating Token Index: 50

Text #16

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1600619 (The Pile)

Max Activating Token Index: 635

Text #17

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4265. Min Act: -0.0000

Data Index: 1303928 (The Pile)

Max Activating Token Index: 110

Text #18

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3844. Min Act: -0.0000

Data Index: 1269916 (The Pile)

Max Activating Token Index: 448

Text #19

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1939963 (The Pile)

Max Activating Token Index: 588