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

Dataset: The Pile

Neuron 2347 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: 0.6607. Min Range: -0.6607

Max Act: 0.6607. Min Act: -0.0000

Data Index: 1742801 (The Pile)

Max Activating Token Index: 366

Text #1

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1451183 (The Pile)

Max Activating Token Index: 855

Text #2

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.6042. Min Act: -0.0000

Data Index: 1249174 (The Pile)

Max Activating Token Index: 713

Text #3

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.6108. Min Act: -0.0000

Data Index: 490021 (The Pile)

Max Activating Token Index: 478

Text #4

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.5696. Min Act: -0.0000

Data Index: 1909604 (The Pile)

Max Activating Token Index: 365

Text #5

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.5616. Min Act: -0.0000

Data Index: 1924903 (The Pile)

Max Activating Token Index: 196

Text #6

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.5755. Min Act: -0.0000

Data Index: 1092451 (The Pile)

Max Activating Token Index: 54

Text #7

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1421846 (The Pile)

Max Activating Token Index: 93

Text #8

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.5314. Min Act: -0.0000

Data Index: 1760856 (The Pile)

Max Activating Token Index: 213

Text #9

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.5190. Min Act: -0.0000

Data Index: 582601 (The Pile)

Max Activating Token Index: 997

Text #10

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.4771. Min Act: -0.0000

Data Index: 1280961 (The Pile)

Max Activating Token Index: 586

Text #11

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.5222. Min Act: -0.0000

Data Index: 1009066 (The Pile)

Max Activating Token Index: 550

Text #12

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.5188. Min Act: -0.0000

Data Index: 666089 (The Pile)

Max Activating Token Index: 959

Text #13

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1852904 (The Pile)

Max Activating Token Index: 650

Text #14

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.4806. Min Act: -0.0000

Data Index: 501525 (The Pile)

Max Activating Token Index: 838

Text #15

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.4848. Min Act: -0.0000

Data Index: 1062618 (The Pile)

Max Activating Token Index: 151

Text #16

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.5151. Min Act: -0.0000

Data Index: 753471 (The Pile)

Max Activating Token Index: 46

Text #17

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.4786. Min Act: -0.0000

Data Index: 912755 (The Pile)

Max Activating Token Index: 558

Text #18

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1254946 (The Pile)

Max Activating Token Index: 404

Text #19

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.4767. Min Act: -0.0000

Data Index: 908834 (The Pile)

Max Activating Token Index: 983