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

Dataset: The Pile

Neuron 3771 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: 5.2829. Min Range: -5.2829

Max Act: 5.0429. Min Act: -0.0000

Data Index: 893657 (The Pile)

Max Activating Token Index: 368

Text #1

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.3080. Min Act: -0.0000

Data Index: 1772950 (The Pile)

Max Activating Token Index: 632

Text #2

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.7581. Min Act: -0.0000

Data Index: 1666166 (The Pile)

Max Activating Token Index: 771

Text #3

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.8646. Min Act: -0.0000

Data Index: 506563 (The Pile)

Max Activating Token Index: 901

Text #4

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.2506. Min Act: -0.0000

Data Index: 677682 (The Pile)

Max Activating Token Index: 774

Text #5

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.7092. Min Act: -0.0000

Data Index: 440015 (The Pile)

Max Activating Token Index: 722

Text #6

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.1239. Min Act: -0.0000

Data Index: 347304 (The Pile)

Max Activating Token Index: 647

Text #7

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.6005. Min Act: -0.0000

Data Index: 560315 (The Pile)

Max Activating Token Index: 666

Text #8

Max Range: 5.2829. Min Range: -5.2829

Max Act: 3.7700. Min Act: -0.0000

Data Index: 187682 (The Pile)

Max Activating Token Index: 948

Text #9

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.3220. Min Act: -0.0000

Data Index: 1965254 (The Pile)

Max Activating Token Index: 770

Text #10

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.1698. Min Act: -0.0000

Data Index: 585192 (The Pile)

Max Activating Token Index: 685

Text #11

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.7566. Min Act: -0.0000

Data Index: 1102427 (The Pile)

Max Activating Token Index: 834

Text #12

Max Range: 5.2829. Min Range: -5.2829

Max Act: 5.2829. Min Act: -0.0000

Data Index: 543504 (The Pile)

Max Activating Token Index: 864

Text #13

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.2128. Min Act: -0.0000

Data Index: 686540 (The Pile)

Max Activating Token Index: 507

Text #14

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.4950. Min Act: -0.0000

Data Index: 686684 (The Pile)

Max Activating Token Index: 639

Text #15

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.2500. Min Act: -0.0000

Data Index: 1426208 (The Pile)

Max Activating Token Index: 645

Text #16

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.4062. Min Act: -0.0000

Data Index: 699577 (The Pile)

Max Activating Token Index: 329

Text #17

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.1883. Min Act: -0.0000

Data Index: 309091 (The Pile)

Max Activating Token Index: 712

Text #18

Max Range: 5.2829. Min Range: -5.2829

Max Act: 4.0557. Min Act: -0.0000

Data Index: 148659 (The Pile)

Max Activating Token Index: 402

Text #19

Max Range: 5.2829. Min Range: -5.2829

Max Act: 3.7354. Min Act: -0.0000

Data Index: 1047496 (The Pile)

Max Activating Token Index: 670