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

Dataset: The Pile

Neuron 4389 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: 0.2718. Min Range: -0.2718

Max Act: 0.2718. Min Act: -0.0000

Data Index: 390706 (The Pile)

Max Activating Token Index: 60

Text #1

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1123596 (The Pile)

Max Activating Token Index: 890

Text #2

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1984807 (The Pile)

Max Activating Token Index: 548

Text #3

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2654. Min Act: -0.0000

Data Index: 1602396 (The Pile)

Max Activating Token Index: 404

Text #4

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1966349 (The Pile)

Max Activating Token Index: 937

Text #5

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2405. Min Act: -0.0000

Data Index: 251888 (The Pile)

Max Activating Token Index: 373

Text #6

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2439. Min Act: -0.0000

Data Index: 1233581 (The Pile)

Max Activating Token Index: 481

Text #7

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2491. Min Act: -0.0000

Data Index: 406750 (The Pile)

Max Activating Token Index: 889

Text #8

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2396. Min Act: -0.0000

Data Index: 1227907 (The Pile)

Max Activating Token Index: 992

Text #9

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2216. Min Act: -0.0001

Data Index: 259836 (The Pile)

Max Activating Token Index: 485

Text #10

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2223. Min Act: -0.0000

Data Index: 901855 (The Pile)

Max Activating Token Index: 676

Text #11

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2175. Min Act: -0.0000

Data Index: 426239 (The Pile)

Max Activating Token Index: 882

Text #12

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2238. Min Act: -0.0000

Data Index: 840618 (The Pile)

Max Activating Token Index: 73

Text #13

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2183. Min Act: -0.0000

Data Index: 496351 (The Pile)

Max Activating Token Index: 477

Text #14

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1505737 (The Pile)

Max Activating Token Index: 195

Text #15

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2453. Min Act: -0.0000

Data Index: 697379 (The Pile)

Max Activating Token Index: 405

Text #16

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2316. Min Act: -0.0000

Data Index: 957269 (The Pile)

Max Activating Token Index: 201

Text #17

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2036. Min Act: -0.0000

Data Index: 321630 (The Pile)

Max Activating Token Index: 843

Text #18

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1788813 (The Pile)

Max Activating Token Index: 965

Text #19

Max Range: 0.2718. Min Range: -0.2718

Max Act: 0.2195. Min Act: -0.0000

Data Index: 410438 (The Pile)

Max Activating Token Index: 177