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

Dataset: The Pile

Neuron 2278 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: 0.6386. Min Range: -0.6386

Max Act: 0.6320. Min Act: -0.0000

Data Index: 766885 (The Pile)

Max Activating Token Index: 372

Text #1

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.6386. Min Act: -0.0000

Data Index: 939555 (The Pile)

Max Activating Token Index: 687

Text #2

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1719850 (The Pile)

Max Activating Token Index: 223

Text #3

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5827. Min Act: -0.0000

Data Index: 406194 (The Pile)

Max Activating Token Index: 417

Text #4

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5747. Min Act: -0.0000

Data Index: 557733 (The Pile)

Max Activating Token Index: 544

Text #5

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1187513 (The Pile)

Max Activating Token Index: 657

Text #6

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5313. Min Act: -0.0000

Data Index: 766432 (The Pile)

Max Activating Token Index: 890

Text #7

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5115. Min Act: -0.0000

Data Index: 1410716 (The Pile)

Max Activating Token Index: 426

Text #8

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5077. Min Act: -0.0000

Data Index: 916234 (The Pile)

Max Activating Token Index: 799

Text #9

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1995252 (The Pile)

Max Activating Token Index: 617

Text #10

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5388. Min Act: -0.0000

Data Index: 976424 (The Pile)

Max Activating Token Index: 707

Text #11

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1433431 (The Pile)

Max Activating Token Index: 1009

Text #12

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5315. Min Act: -0.0000

Data Index: 6903 (The Pile)

Max Activating Token Index: 143

Text #13

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5229. Min Act: -0.0000

Data Index: 773951 (The Pile)

Max Activating Token Index: 324

Text #14

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4863. Min Act: -0.0000

Data Index: 1773105 (The Pile)

Max Activating Token Index: 484

Text #15

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4763. Min Act: -0.0000

Data Index: 1116061 (The Pile)

Max Activating Token Index: 390

Text #16

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1576935 (The Pile)

Max Activating Token Index: 393

Text #17

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4797. Min Act: -0.0000

Data Index: 658950 (The Pile)

Max Activating Token Index: 356

Text #18

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.4914. Min Act: -0.0000

Data Index: 367867 (The Pile)

Max Activating Token Index: 240

Text #19

Max Range: 0.6386. Min Range: -0.6386

Max Act: 0.5146. Min Act: -0.0000

Data Index: 350570 (The Pile)

Max Activating Token Index: 802