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

Dataset: The Pile

Neuron 3936 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: 1.0471. Min Range: -1.0471

Max Act: 1.0471. Min Act: -0.0000

Data Index: 1959829 (The Pile)

Max Activating Token Index: 364

Text #1

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.9862. Min Act: -0.0000

Data Index: 232342 (The Pile)

Max Activating Token Index: 719

Text #2

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.9200. Min Act: -0.0000

Data Index: 120083 (The Pile)

Max Activating Token Index: 58

Text #3

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.8533. Min Act: -0.0000

Data Index: 1125420 (The Pile)

Max Activating Token Index: 450

Text #4

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.8518. Min Act: -0.0000

Data Index: 558783 (The Pile)

Max Activating Token Index: 347

Text #5

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.7652. Min Act: -0.0000

Data Index: 1105141 (The Pile)

Max Activating Token Index: 852

Text #6

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.7872. Min Act: -0.0000

Data Index: 1813975 (The Pile)

Max Activating Token Index: 666

Text #7

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1726701 (The Pile)

Max Activating Token Index: 582

Text #8

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.7238. Min Act: -0.0000

Data Index: 1615934 (The Pile)

Max Activating Token Index: 250

Text #9

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.7245. Min Act: -0.0000

Data Index: 549989 (The Pile)

Max Activating Token Index: 97

Text #10

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.7337. Min Act: -0.0000

Data Index: 1352222 (The Pile)

Max Activating Token Index: 614

Text #11

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.7225. Min Act: -0.0000

Data Index: 503075 (The Pile)

Max Activating Token Index: 653

Text #12

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.6770. Min Act: -0.0000

Data Index: 1911316 (The Pile)

Max Activating Token Index: 789

Text #13

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.6706. Min Act: -0.0000

Data Index: 174710 (The Pile)

Max Activating Token Index: 414

Text #14

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.7078. Min Act: -0.0000

Data Index: 731230 (The Pile)

Max Activating Token Index: 46

Text #15

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.6243. Min Act: -0.0000

Data Index: 904051 (The Pile)

Max Activating Token Index: 93

Text #16

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.7007. Min Act: -0.0000

Data Index: 1766527 (The Pile)

Max Activating Token Index: 99

Text #17

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1032640 (The Pile)

Max Activating Token Index: 209

Text #18

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.7244. Min Act: -0.0000

Data Index: 337623 (The Pile)

Max Activating Token Index: 152

Text #19

Max Range: 1.0471. Min Range: -1.0471

Max Act: 0.6625. Min Act: -0.0000

Data Index: 764371 (The Pile)

Max Activating Token Index: 1008