Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 776 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.6384. Min Act: -0.0000

Data Index: 315304 (The Pile)

Max Activating Token Index: 502

Text #1

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.6519. Min Act: -0.0000

Data Index: 1998682 (The Pile)

Max Activating Token Index: 688

Text #2

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.5484. Min Act: -0.0000

Data Index: 1540253 (The Pile)

Max Activating Token Index: 296

Text #3

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4848. Min Act: -0.0000

Data Index: 1914272 (The Pile)

Max Activating Token Index: 550

Text #4

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4793. Min Act: -0.0000

Data Index: 980524 (The Pile)

Max Activating Token Index: 942

Text #5

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4616. Min Act: 0.0000

Data Index: 1820555 (The Pile)

Max Activating Token Index: 386

Text #6

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.5063. Min Act: -0.0000

Data Index: 1221146 (The Pile)

Max Activating Token Index: 90

Text #7

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1382498 (The Pile)

Max Activating Token Index: 660

Text #8

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.5064. Min Act: -0.0000

Data Index: 241802 (The Pile)

Max Activating Token Index: 1010

Text #9

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4474. Min Act: -0.0000

Data Index: 1638369 (The Pile)

Max Activating Token Index: 769

Text #10

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4392. Min Act: -0.0000

Data Index: 1988355 (The Pile)

Max Activating Token Index: 329

Text #11

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4229. Min Act: -0.0000

Data Index: 436018 (The Pile)

Max Activating Token Index: 760

Text #12

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1135518 (The Pile)

Max Activating Token Index: 1010

Text #13

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4598. Min Act: -0.0000

Data Index: 1818942 (The Pile)

Max Activating Token Index: 679

Text #14

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4575. Min Act: -0.0000

Data Index: 1216211 (The Pile)

Max Activating Token Index: 859

Text #15

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4238. Min Act: -0.0000

Data Index: 359011 (The Pile)

Max Activating Token Index: 891

Text #16

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4404. Min Act: -0.0000

Data Index: 328538 (The Pile)

Max Activating Token Index: 963

Text #17

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.4441. Min Act: -0.0000

Data Index: 185241 (The Pile)

Max Activating Token Index: 487

Text #18

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.3923. Min Act: -0.0000

Data Index: 380450 (The Pile)

Max Activating Token Index: 879

Text #19

Max Range: 0.6519. Min Range: -0.6519

Max Act: 0.3978. Min Act: -0.0000

Data Index: 1013689 (The Pile)

Max Activating Token Index: 914