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

Dataset: The Pile

Neuron 80 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0635. Min Range: -1.0635

Max Act: 1.0635. Min Act: -0.0000

Data Index: 1243680 (The Pile)

Max Activating Token Index: 835

Text #1

Max Range: 1.0635. Min Range: -1.0635

Max Act: 1.0255. Min Act: -0.0000

Data Index: 950921 (The Pile)

Max Activating Token Index: 671

Text #2

Max Range: 1.0635. Min Range: -1.0635

Max Act: 1.0528. Min Act: -0.0000

Data Index: 1568027 (The Pile)

Max Activating Token Index: 509

Text #3

Max Range: 1.0635. Min Range: -1.0635

Max Act: 1.0140. Min Act: -0.0000

Data Index: 1841915 (The Pile)

Max Activating Token Index: 615

Text #4

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9513. Min Act: -0.0000

Data Index: 653050 (The Pile)

Max Activating Token Index: 855

Text #5

Max Range: 1.0635. Min Range: -1.0635

Max Act: 1.0218. Min Act: -0.0000

Data Index: 337194 (The Pile)

Max Activating Token Index: 953

Text #6

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9877. Min Act: -0.0000

Data Index: 630752 (The Pile)

Max Activating Token Index: 562

Text #7

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9137. Min Act: -0.0000

Data Index: 174163 (The Pile)

Max Activating Token Index: 119

Text #8

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9643. Min Act: -0.0000

Data Index: 1992349 (The Pile)

Max Activating Token Index: 854

Text #9

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9353. Min Act: -0.0000

Data Index: 269506 (The Pile)

Max Activating Token Index: 349

Text #10

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9444. Min Act: -0.0000

Data Index: 803483 (The Pile)

Max Activating Token Index: 147

Text #11

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9076. Min Act: -0.0000

Data Index: 1539119 (The Pile)

Max Activating Token Index: 416

Text #12

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9324. Min Act: -0.0000

Data Index: 70015 (The Pile)

Max Activating Token Index: 557

Text #13

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9579. Min Act: -0.0000

Data Index: 981016 (The Pile)

Max Activating Token Index: 433

Text #14

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9568. Min Act: -0.0000

Data Index: 391111 (The Pile)

Max Activating Token Index: 791

Text #15

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9184. Min Act: -0.0000

Data Index: 1065828 (The Pile)

Max Activating Token Index: 759

Text #16

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9371. Min Act: -0.0000

Data Index: 1713119 (The Pile)

Max Activating Token Index: 933

Text #17

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9790. Min Act: -0.0000

Data Index: 1814466 (The Pile)

Max Activating Token Index: 224

Text #18

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9352. Min Act: -0.0000

Data Index: 1516110 (The Pile)

Max Activating Token Index: 609

Text #19

Max Range: 1.0635. Min Range: -1.0635

Max Act: 0.9932. Min Act: -0.0000

Data Index: 1511536 (The Pile)

Max Activating Token Index: 484