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

Dataset: The Pile

Neuron 4436 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.3333. Min Act: -0.0000

Data Index: 585396 (The Pile)

Max Activating Token Index: 36

Text #1

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1785872 (The Pile)

Max Activating Token Index: 458

Text #2

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2680. Min Act: -0.0000

Data Index: 1147560 (The Pile)

Max Activating Token Index: 59

Text #3

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2413. Min Act: -0.0000

Data Index: 442422 (The Pile)

Max Activating Token Index: 523

Text #4

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2432. Min Act: -0.0000

Data Index: 568490 (The Pile)

Max Activating Token Index: 545

Text #5

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1763501 (The Pile)

Max Activating Token Index: 119

Text #6

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2309. Min Act: -0.0000

Data Index: 1300101 (The Pile)

Max Activating Token Index: 808

Text #7

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2193. Min Act: -0.0000

Data Index: 703801 (The Pile)

Max Activating Token Index: 123

Text #8

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2334. Min Act: -0.0000

Data Index: 1324197 (The Pile)

Max Activating Token Index: 479

Text #9

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1897827 (The Pile)

Max Activating Token Index: 314

Text #10

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2109. Min Act: -0.0000

Data Index: 659975 (The Pile)

Max Activating Token Index: 391

Text #11

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2179. Min Act: -0.0000

Data Index: 1148520 (The Pile)

Max Activating Token Index: 645

Text #12

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2089. Min Act: -0.0000

Data Index: 816747 (The Pile)

Max Activating Token Index: 419

Text #13

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.1996. Min Act: -0.0000

Data Index: 410377 (The Pile)

Max Activating Token Index: 929

Text #14

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.1965. Min Act: -0.0000

Data Index: 838108 (The Pile)

Max Activating Token Index: 359

Text #15

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1482992 (The Pile)

Max Activating Token Index: 877

Text #16

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1323937 (The Pile)

Max Activating Token Index: 583

Text #17

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2073. Min Act: -0.0000

Data Index: 289604 (The Pile)

Max Activating Token Index: 435

Text #18

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.2056. Min Act: -0.0000

Data Index: 631442 (The Pile)

Max Activating Token Index: 434

Text #19

Max Range: 0.3333. Min Range: -0.3333

Max Act: 0.1864. Min Act: -0.0000

Data Index: 165659 (The Pile)

Max Activating Token Index: 905