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

Dataset: The Pile

Neuron 420 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: 0.8478. Min Range: -0.8478

Max Act: 0.8063. Min Act: -0.0000

Data Index: 1384479 (The Pile)

Max Activating Token Index: 362

Text #1

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7361. Min Act: -0.0000

Data Index: 1602850 (The Pile)

Max Activating Token Index: 799

Text #2

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.8478. Min Act: -0.0000

Data Index: 32183 (The Pile)

Max Activating Token Index: 915

Text #3

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7862. Min Act: -0.0000

Data Index: 1868296 (The Pile)

Max Activating Token Index: 620

Text #4

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7520. Min Act: -0.0000

Data Index: 1624269 (The Pile)

Max Activating Token Index: 830

Text #5

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7882. Min Act: -0.0000

Data Index: 747615 (The Pile)

Max Activating Token Index: 858

Text #6

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1762171 (The Pile)

Max Activating Token Index: 882

Text #7

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7336. Min Act: -0.0000

Data Index: 1508015 (The Pile)

Max Activating Token Index: 273

Text #8

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6862. Min Act: -0.0000

Data Index: 1872902 (The Pile)

Max Activating Token Index: 917

Text #9

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1301908 (The Pile)

Max Activating Token Index: 752

Text #10

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7000. Min Act: -0.0000

Data Index: 224669 (The Pile)

Max Activating Token Index: 833

Text #11

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7156. Min Act: -0.0000

Data Index: 1555630 (The Pile)

Max Activating Token Index: 990

Text #12

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1178190 (The Pile)

Max Activating Token Index: 320

Text #13

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7234. Min Act: -0.0000

Data Index: 1470804 (The Pile)

Max Activating Token Index: 198

Text #14

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6972. Min Act: -0.0000

Data Index: 1925573 (The Pile)

Max Activating Token Index: 573

Text #15

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6782. Min Act: -0.0000

Data Index: 69445 (The Pile)

Max Activating Token Index: 479

Text #16

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7159. Min Act: -0.0000

Data Index: 1785475 (The Pile)

Max Activating Token Index: 267

Text #17

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6742. Min Act: -0.0000

Data Index: 362258 (The Pile)

Max Activating Token Index: 367

Text #18

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1965709 (The Pile)

Max Activating Token Index: 425

Text #19

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6562. Min Act: -0.0000

Data Index: 19230 (The Pile)

Max Activating Token Index: 509