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

Dataset: The Pile

Neuron 3969 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.4495. Min Act: -0.0000

Data Index: 294916 (The Pile)

Max Activating Token Index: 993

Text #1

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.3610. Min Act: -0.0000

Data Index: 607356 (The Pile)

Max Activating Token Index: 27

Text #2

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.3459. Min Act: -0.0001

Data Index: 306418 (The Pile)

Max Activating Token Index: 328

Text #3

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.2692. Min Act: -0.0001

Data Index: 1552627 (The Pile)

Max Activating Token Index: 725

Text #4

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.2363. Min Act: -0.0000

Data Index: 1193781 (The Pile)

Max Activating Token Index: 605

Text #5

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.1904. Min Act: -0.0000

Data Index: 172614 (The Pile)

Max Activating Token Index: 979

Text #6

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.1356. Min Act: -0.0000

Data Index: 1233838 (The Pile)

Max Activating Token Index: 896

Text #7

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.1717. Min Act: -0.0000

Data Index: 628778 (The Pile)

Max Activating Token Index: 953

Text #8

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.1670. Min Act: -0.0000

Data Index: 1745412 (The Pile)

Max Activating Token Index: 293

Text #9

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.1805. Min Act: -0.0000

Data Index: 1981105 (The Pile)

Max Activating Token Index: 134

Text #10

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.1689. Min Act: -0.0000

Data Index: 615036 (The Pile)

Max Activating Token Index: 966

Text #11

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.1403. Min Act: -0.0000

Data Index: 367101 (The Pile)

Max Activating Token Index: 838

Text #12

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.1119. Min Act: -0.0001

Data Index: 76482 (The Pile)

Max Activating Token Index: 534

Text #13

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.0138. Min Act: -0.0000

Data Index: 1544707 (The Pile)

Max Activating Token Index: 1017

Text #14

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.1147. Min Act: -0.0000

Data Index: 620585 (The Pile)

Max Activating Token Index: 662

Text #15

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.0715. Min Act: -0.0000

Data Index: 1365018 (The Pile)

Max Activating Token Index: 925

Text #16

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.1320. Min Act: -0.0000

Data Index: 1680866 (The Pile)

Max Activating Token Index: 935

Text #17

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.1262. Min Act: -0.0000

Data Index: 1347487 (The Pile)

Max Activating Token Index: 924

Text #18

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.0635. Min Act: -0.0000

Data Index: 1361817 (The Pile)

Max Activating Token Index: 660

Text #19

Max Range: 1.4495. Min Range: -1.4495

Max Act: 1.1207. Min Act: -0.0000

Data Index: 1996391 (The Pile)

Max Activating Token Index: 420