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

Dataset: The Pile

Neuron 546 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: 0.2983. Min Range: -0.2983

Max Act: 0.2983. Min Act: -0.0000

Data Index: 650195 (The Pile)

Max Activating Token Index: 388

Text #1

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2848. Min Act: -0.0000

Data Index: 928555 (The Pile)

Max Activating Token Index: 651

Text #2

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2568. Min Act: -0.0000

Data Index: 1814352 (The Pile)

Max Activating Token Index: 293

Text #3

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2454. Min Act: -0.0000

Data Index: 1607013 (The Pile)

Max Activating Token Index: 837

Text #4

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1793210 (The Pile)

Max Activating Token Index: 819

Text #5

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2264. Min Act: -0.0000

Data Index: 1481377 (The Pile)

Max Activating Token Index: 1016

Text #6

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2365. Min Act: -0.0000

Data Index: 1051448 (The Pile)

Max Activating Token Index: 535

Text #7

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1588443 (The Pile)

Max Activating Token Index: 235

Text #8

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2425. Min Act: -0.0000

Data Index: 778217 (The Pile)

Max Activating Token Index: 665

Text #9

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2282. Min Act: -0.0000

Data Index: 1407731 (The Pile)

Max Activating Token Index: 920

Text #10

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1520729 (The Pile)

Max Activating Token Index: 540

Text #11

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1078518 (The Pile)

Max Activating Token Index: 774

Text #12

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2284. Min Act: -0.0000

Data Index: 1411973 (The Pile)

Max Activating Token Index: 317

Text #13

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2187. Min Act: -0.0000

Data Index: 48941 (The Pile)

Max Activating Token Index: 946

Text #14

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2252. Min Act: -0.0000

Data Index: 32858 (The Pile)

Max Activating Token Index: 38

Text #15

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2309. Min Act: -0.0000

Data Index: 1681544 (The Pile)

Max Activating Token Index: 166

Text #16

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2218. Min Act: -0.0000

Data Index: 531570 (The Pile)

Max Activating Token Index: 541

Text #17

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2204. Min Act: -0.0000

Data Index: 285964 (The Pile)

Max Activating Token Index: 279

Text #18

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2116. Min Act: -0.0000

Data Index: 1924268 (The Pile)

Max Activating Token Index: 850

Text #19

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2141. Min Act: 0.0000

Data Index: 1769974 (The Pile)

Max Activating Token Index: 525