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

Dataset: The Pile

Neuron 1734 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0225. Min Act: -0.0000

Data Index: 893507 (The Pile)

Max Activating Token Index: 370

Text #1

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0213. Min Act: -0.0000

Data Index: 1462665 (The Pile)

Max Activating Token Index: 670

Text #2

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0206. Min Act: -0.0000

Data Index: 1430771 (The Pile)

Max Activating Token Index: 511

Text #3

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0199. Min Act: -0.0000

Data Index: 1421537 (The Pile)

Max Activating Token Index: 803

Text #4

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0198. Min Act: -0.0000

Data Index: 1556783 (The Pile)

Max Activating Token Index: 714

Text #5

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0198. Min Act: -0.0000

Data Index: 265985 (The Pile)

Max Activating Token Index: 518

Text #6

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0198. Min Act: -0.0000

Data Index: 1870545 (The Pile)

Max Activating Token Index: 440

Text #7

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0197. Min Act: -0.0000

Data Index: 1019053 (The Pile)

Max Activating Token Index: 588

Text #8

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0201. Min Act: -0.0000

Data Index: 366855 (The Pile)

Max Activating Token Index: 774

Text #9

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0192. Min Act: -0.0000

Data Index: 488283 (The Pile)

Max Activating Token Index: 843

Text #10

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0191. Min Act: -0.0000

Data Index: 1028713 (The Pile)

Max Activating Token Index: 344

Text #11

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0191. Min Act: -0.0000

Data Index: 1641732 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0191. Min Act: -0.0000

Data Index: 926846 (The Pile)

Max Activating Token Index: 536

Text #13

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0190. Min Act: -0.0000

Data Index: 1066616 (The Pile)

Max Activating Token Index: 787

Text #14

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0189. Min Act: -0.0000

Data Index: 1002888 (The Pile)

Max Activating Token Index: 619

Text #15

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0189. Min Act: -0.0000

Data Index: 845792 (The Pile)

Max Activating Token Index: 695

Text #16

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0189. Min Act: -0.0000

Data Index: 1516376 (The Pile)

Max Activating Token Index: 525

Text #17

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0188. Min Act: -0.0000

Data Index: 77074 (The Pile)

Max Activating Token Index: 370

Text #18

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0188. Min Act: -0.0000

Data Index: 535984 (The Pile)

Max Activating Token Index: 494

Text #19

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0182. Min Act: -0.0000

Data Index: 1469131 (The Pile)

Max Activating Token Index: 698