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

Dataset: The Pile

Neuron 3858 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: 1.1702. Min Range: -1.1702

Max Act: 1.0818. Min Act: -0.0000

Data Index: 907835 (The Pile)

Max Activating Token Index: 622

Text #1

Max Range: 1.1702. Min Range: -1.1702

Max Act: 1.1300. Min Act: -0.0000

Data Index: 1201396 (The Pile)

Max Activating Token Index: 345

Text #2

Max Range: 1.1702. Min Range: -1.1702

Max Act: 1.1499. Min Act: -0.0000

Data Index: 1422533 (The Pile)

Max Activating Token Index: 671

Text #3

Max Range: 1.1702. Min Range: -1.1702

Max Act: 1.1186. Min Act: -0.0000

Data Index: 1765777 (The Pile)

Max Activating Token Index: 537

Text #4

Max Range: 1.1702. Min Range: -1.1702

Max Act: 1.0501. Min Act: -0.0000

Data Index: 1768754 (The Pile)

Max Activating Token Index: 316

Text #5

Max Range: 1.1702. Min Range: -1.1702

Max Act: 1.0261. Min Act: -0.0000

Data Index: 905924 (The Pile)

Max Activating Token Index: 492

Text #6

Max Range: 1.1702. Min Range: -1.1702

Max Act: 1.0305. Min Act: -0.0000

Data Index: 678893 (The Pile)

Max Activating Token Index: 313

Text #7

Max Range: 1.1702. Min Range: -1.1702

Max Act: 1.0600. Min Act: -0.0000

Data Index: 185094 (The Pile)

Max Activating Token Index: 554

Text #8

Max Range: 1.1702. Min Range: -1.1702

Max Act: 1.0248. Min Act: -0.0000

Data Index: 1514566 (The Pile)

Max Activating Token Index: 468

Text #9

Max Range: 1.1702. Min Range: -1.1702

Max Act: 1.0421. Min Act: -0.0000

Data Index: 1440078 (The Pile)

Max Activating Token Index: 431

Text #10

Max Range: 1.1702. Min Range: -1.1702

Max Act: 1.0555. Min Act: -0.0000

Data Index: 1807484 (The Pile)

Max Activating Token Index: 94

Text #11

Max Range: 1.1702. Min Range: -1.1702

Max Act: 1.0211. Min Act: -0.0000

Data Index: 1008304 (The Pile)

Max Activating Token Index: 440

Text #12

Max Range: 1.1702. Min Range: -1.1702

Max Act: 1.0027. Min Act: -0.0000

Data Index: 918561 (The Pile)

Max Activating Token Index: 210

Text #13

Max Range: 1.1702. Min Range: -1.1702

Max Act: 0.9898. Min Act: -0.0000

Data Index: 1388811 (The Pile)

Max Activating Token Index: 426

Text #14

Max Range: 1.1702. Min Range: -1.1702

Max Act: 1.0177. Min Act: -0.0000

Data Index: 776112 (The Pile)

Max Activating Token Index: 846

Text #15

Max Range: 1.1702. Min Range: -1.1702

Max Act: 1.1702. Min Act: -0.0000

Data Index: 154642 (The Pile)

Max Activating Token Index: 606

Text #16

Max Range: 1.1702. Min Range: -1.1702

Max Act: 0.9487. Min Act: -0.0000

Data Index: 124692 (The Pile)

Max Activating Token Index: 688

Text #17

Max Range: 1.1702. Min Range: -1.1702

Max Act: 1.0019. Min Act: -0.0000

Data Index: 429408 (The Pile)

Max Activating Token Index: 401

Text #18

Max Range: 1.1702. Min Range: -1.1702

Max Act: 1.0653. Min Act: -0.0000

Data Index: 192520 (The Pile)

Max Activating Token Index: 959

Text #19

Max Range: 1.1702. Min Range: -1.1702

Max Act: 1.0303. Min Act: -0.0000

Data Index: 876417 (The Pile)

Max Activating Token Index: 433