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

Dataset: The Pile

Neuron 4903 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: 3.3635. Min Range: -3.3635

Max Act: 3.3635. Min Act: -0.0000

Data Index: 1368317 (The Pile)

Max Activating Token Index: 430

Text #1

Max Range: 3.3635. Min Range: -3.3635

Max Act: 3.0161. Min Act: -0.0000

Data Index: 1164032 (The Pile)

Max Activating Token Index: 401

Text #2

Max Range: 3.3635. Min Range: -3.3635

Max Act: 3.0902. Min Act: -0.0000

Data Index: 1410329 (The Pile)

Max Activating Token Index: 483

Text #3

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.8761. Min Act: -0.0000

Data Index: 1130264 (The Pile)

Max Activating Token Index: 429

Text #4

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.8678. Min Act: -0.0000

Data Index: 869396 (The Pile)

Max Activating Token Index: 837

Text #5

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.8107. Min Act: -0.0000

Data Index: 1384136 (The Pile)

Max Activating Token Index: 798

Text #6

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.7912. Min Act: -0.0000

Data Index: 1819262 (The Pile)

Max Activating Token Index: 338

Text #7

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.6232. Min Act: -0.0000

Data Index: 1066319 (The Pile)

Max Activating Token Index: 613

Text #8

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.7558. Min Act: -0.0000

Data Index: 1953361 (The Pile)

Max Activating Token Index: 387

Text #9

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.3803. Min Act: -0.0000

Data Index: 1901992 (The Pile)

Max Activating Token Index: 967

Text #10

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.4634. Min Act: -0.0000

Data Index: 1273360 (The Pile)

Max Activating Token Index: 477

Text #11

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.6734. Min Act: -0.0000

Data Index: 801171 (The Pile)

Max Activating Token Index: 310

Text #12

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.7991. Min Act: -0.0000

Data Index: 1158833 (The Pile)

Max Activating Token Index: 943

Text #13

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.5288. Min Act: -0.0000

Data Index: 1950127 (The Pile)

Max Activating Token Index: 347

Text #14

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.6599. Min Act: -0.0000

Data Index: 339314 (The Pile)

Max Activating Token Index: 1005

Text #15

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.4123. Min Act: -0.0000

Data Index: 1983299 (The Pile)

Max Activating Token Index: 270

Text #16

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.4972. Min Act: -0.0000

Data Index: 521040 (The Pile)

Max Activating Token Index: 293

Text #17

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.4697. Min Act: -0.0000

Data Index: 1932349 (The Pile)

Max Activating Token Index: 513

Text #18

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.5894. Min Act: -0.0000

Data Index: 596306 (The Pile)

Max Activating Token Index: 421

Text #19

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.5623. Min Act: -0.0000

Data Index: 1732866 (The Pile)

Max Activating Token Index: 548