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

Dataset: The Pile

Neuron 2160 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: 1.1247. Min Range: -1.1247

Max Act: 1.1247. Min Act: -0.0000

Data Index: 25861 (The Pile)

Max Activating Token Index: 468

Text #1

Max Range: 1.1247. Min Range: -1.1247

Max Act: 1.1142. Min Act: -0.0000

Data Index: 708948 (The Pile)

Max Activating Token Index: 29

Text #2

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.9434. Min Act: -0.0000

Data Index: 1430613 (The Pile)

Max Activating Token Index: 669

Text #3

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.9698. Min Act: -0.0000

Data Index: 1258783 (The Pile)

Max Activating Token Index: 437

Text #4

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.9451. Min Act: -0.0000

Data Index: 930699 (The Pile)

Max Activating Token Index: 257

Text #5

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.9330. Min Act: -0.0000

Data Index: 1995526 (The Pile)

Max Activating Token Index: 973

Text #6

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.9950. Min Act: -0.0000

Data Index: 1166272 (The Pile)

Max Activating Token Index: 641

Text #7

Max Range: 1.1247. Min Range: -1.1247

Max Act: 1.0270. Min Act: -0.0000

Data Index: 1976614 (The Pile)

Max Activating Token Index: 122

Text #8

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1651169 (The Pile)

Max Activating Token Index: 789

Text #9

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.9247. Min Act: -0.0000

Data Index: 1341582 (The Pile)

Max Activating Token Index: 497

Text #10

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.8489. Min Act: -0.0000

Data Index: 1037372 (The Pile)

Max Activating Token Index: 294

Text #11

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.8738. Min Act: -0.0000

Data Index: 988416 (The Pile)

Max Activating Token Index: 992

Text #12

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.8868. Min Act: -0.0000

Data Index: 216690 (The Pile)

Max Activating Token Index: 12

Text #13

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.8243. Min Act: -0.0000

Data Index: 921333 (The Pile)

Max Activating Token Index: 742

Text #14

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.8845. Min Act: -0.0000

Data Index: 394888 (The Pile)

Max Activating Token Index: 489

Text #15

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.8424. Min Act: -0.0000

Data Index: 605020 (The Pile)

Max Activating Token Index: 536

Text #16

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.8382. Min Act: -0.0000

Data Index: 1167892 (The Pile)

Max Activating Token Index: 575

Text #17

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.7349. Min Act: -0.0000

Data Index: 808731 (The Pile)

Max Activating Token Index: 569

Text #18

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.8919. Min Act: -0.0000

Data Index: 395580 (The Pile)

Max Activating Token Index: 21

Text #19

Max Range: 1.1247. Min Range: -1.1247

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1194568 (The Pile)

Max Activating Token Index: 867