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

Dataset: The Pile

Neuron 3884 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: 1.5154. Min Range: -1.5154

Max Act: 1.4675. Min Act: -0.0000

Data Index: 1721067 (The Pile)

Max Activating Token Index: 903

Text #1

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.5154. Min Act: -0.0000

Data Index: 147213 (The Pile)

Max Activating Token Index: 450

Text #2

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.0954. Min Act: -0.0000

Data Index: 1437999 (The Pile)

Max Activating Token Index: 543

Text #3

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.2270. Min Act: -0.0000

Data Index: 314203 (The Pile)

Max Activating Token Index: 694

Text #4

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.0969. Min Act: -0.0000

Data Index: 1855657 (The Pile)

Max Activating Token Index: 589

Text #5

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.0499. Min Act: -0.0000

Data Index: 1113327 (The Pile)

Max Activating Token Index: 807

Text #6

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.1031. Min Act: -0.0000

Data Index: 935092 (The Pile)

Max Activating Token Index: 633

Text #7

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.0959. Min Act: -0.0000

Data Index: 259669 (The Pile)

Max Activating Token Index: 706

Text #8

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.0731. Min Act: -0.0000

Data Index: 1874891 (The Pile)

Max Activating Token Index: 119

Text #9

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.1393. Min Act: -0.0000

Data Index: 1925864 (The Pile)

Max Activating Token Index: 629

Text #10

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.1180. Min Act: -0.0000

Data Index: 1840591 (The Pile)

Max Activating Token Index: 548

Text #11

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.9326. Min Act: -0.0000

Data Index: 1297625 (The Pile)

Max Activating Token Index: 887

Text #12

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.0005. Min Act: -0.0000

Data Index: 18971 (The Pile)

Max Activating Token Index: 469

Text #13

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.9420. Min Act: -0.0000

Data Index: 1651976 (The Pile)

Max Activating Token Index: 558

Text #14

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.9289. Min Act: -0.0000

Data Index: 1824726 (The Pile)

Max Activating Token Index: 742

Text #15

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.9699. Min Act: -0.0000

Data Index: 1782610 (The Pile)

Max Activating Token Index: 600

Text #16

Max Range: 1.5154. Min Range: -1.5154

Max Act: 1.0140. Min Act: -0.0000

Data Index: 1483191 (The Pile)

Max Activating Token Index: 562

Text #17

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.8966. Min Act: -0.0000

Data Index: 802516 (The Pile)

Max Activating Token Index: 995

Text #18

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1417026 (The Pile)

Max Activating Token Index: 383

Text #19

Max Range: 1.5154. Min Range: -1.5154

Max Act: 0.9101. Min Act: -0.0000

Data Index: 325315 (The Pile)

Max Activating Token Index: 1002