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

Dataset: The Pile

Neuron 179 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.3379. Min Act: -0.0000

Data Index: 1687340 (The Pile)

Max Activating Token Index: 858

Text #1

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.3219. Min Act: -0.0000

Data Index: 511424 (The Pile)

Max Activating Token Index: 297

Text #2

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2679. Min Act: -0.0000

Data Index: 608446 (The Pile)

Max Activating Token Index: 730

Text #3

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2632. Min Act: -0.0000

Data Index: 1333105 (The Pile)

Max Activating Token Index: 726

Text #4

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2613. Min Act: -0.0000

Data Index: 357450 (The Pile)

Max Activating Token Index: 152

Text #5

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2482. Min Act: -0.0000

Data Index: 1887177 (The Pile)

Max Activating Token Index: 333

Text #6

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2299. Min Act: -0.0000

Data Index: 665094 (The Pile)

Max Activating Token Index: 737

Text #7

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2336. Min Act: -0.0000

Data Index: 405642 (The Pile)

Max Activating Token Index: 879

Text #8

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1606915 (The Pile)

Max Activating Token Index: 154

Text #9

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2483. Min Act: -0.0000

Data Index: 725711 (The Pile)

Max Activating Token Index: 1018

Text #10

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2290. Min Act: -0.0000

Data Index: 912473 (The Pile)

Max Activating Token Index: 825

Text #11

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2205. Min Act: -0.0000

Data Index: 763459 (The Pile)

Max Activating Token Index: 224

Text #12

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2193. Min Act: -0.0000

Data Index: 100773 (The Pile)

Max Activating Token Index: 661

Text #13

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2297. Min Act: -0.0000

Data Index: 953814 (The Pile)

Max Activating Token Index: 66

Text #14

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2231. Min Act: -0.0000

Data Index: 774 (The Pile)

Max Activating Token Index: 274

Text #15

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2179. Min Act: -0.0000

Data Index: 439442 (The Pile)

Max Activating Token Index: 643

Text #16

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2168. Min Act: -0.0000

Data Index: 461623 (The Pile)

Max Activating Token Index: 809

Text #17

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2148. Min Act: -0.0000

Data Index: 401160 (The Pile)

Max Activating Token Index: 998

Text #18

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.1997. Min Act: -0.0000

Data Index: 579675 (The Pile)

Max Activating Token Index: 934

Text #19

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2143. Min Act: -0.0000

Data Index: 620728 (The Pile)

Max Activating Token Index: 247