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

Dataset: The Pile

Neuron 158 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: 5.5547. Min Range: -5.5547

Max Act: 5.5547. Min Act: -0.0000

Data Index: 1540170 (The Pile)

Max Activating Token Index: 623

Text #1

Max Range: 5.5547. Min Range: -5.5547

Max Act: 5.5331. Min Act: -0.0000

Data Index: 1879980 (The Pile)

Max Activating Token Index: 1021

Text #2

Max Range: 5.5547. Min Range: -5.5547

Max Act: 5.3863. Min Act: -0.0000

Data Index: 851886 (The Pile)

Max Activating Token Index: 401

Text #3

Max Range: 5.5547. Min Range: -5.5547

Max Act: 4.8401. Min Act: 0.0000

Data Index: 1865143 (The Pile)

Max Activating Token Index: 971

Text #4

Max Range: 5.5547. Min Range: -5.5547

Max Act: 4.6936. Min Act: -0.0000

Data Index: 1259093 (The Pile)

Max Activating Token Index: 714

Text #5

Max Range: 5.5547. Min Range: -5.5547

Max Act: 4.6739. Min Act: -0.0000

Data Index: 1186259 (The Pile)

Max Activating Token Index: 415

Text #6

Max Range: 5.5547. Min Range: -5.5547

Max Act: 4.1625. Min Act: -0.0000

Data Index: 1422830 (The Pile)

Max Activating Token Index: 391

Text #7

Max Range: 5.5547. Min Range: -5.5547

Max Act: 4.2557. Min Act: -0.0000

Data Index: 1273902 (The Pile)

Max Activating Token Index: 394

Text #8

Max Range: 5.5547. Min Range: -5.5547

Max Act: 4.1960. Min Act: -0.0000

Data Index: 1399092 (The Pile)

Max Activating Token Index: 940

Text #9

Max Range: 5.5547. Min Range: -5.5547

Max Act: 3.8544. Min Act: 0.0000

Data Index: 1876316 (The Pile)

Max Activating Token Index: 934

Text #10

Max Range: 5.5547. Min Range: -5.5547

Max Act: 3.9492. Min Act: -0.0000

Data Index: 1991520 (The Pile)

Max Activating Token Index: 818

Text #11

Max Range: 5.5547. Min Range: -5.5547

Max Act: 4.0603. Min Act: 0.0000

Data Index: 454996 (The Pile)

Max Activating Token Index: 982

Text #12

Max Range: 5.5547. Min Range: -5.5547

Max Act: 3.3044. Min Act: 0.0000

Data Index: 191478 (The Pile)

Max Activating Token Index: 1004

Text #13

Max Range: 5.5547. Min Range: -5.5547

Max Act: 4.1709. Min Act: -0.0000

Data Index: 908370 (The Pile)

Max Activating Token Index: 604

Text #14

Max Range: 5.5547. Min Range: -5.5547

Max Act: 3.9416. Min Act: -0.0000

Data Index: 1892832 (The Pile)

Max Activating Token Index: 355

Text #15

Max Range: 5.5547. Min Range: -5.5547

Max Act: 3.6349. Min Act: -0.0000

Data Index: 1358404 (The Pile)

Max Activating Token Index: 704

Text #16

Max Range: 5.5547. Min Range: -5.5547

Max Act: 3.7634. Min Act: -0.0000

Data Index: 1979620 (The Pile)

Max Activating Token Index: 87

Text #17

Max Range: 5.5547. Min Range: -5.5547

Max Act: 3.5421. Min Act: -0.0000

Data Index: 797457 (The Pile)

Max Activating Token Index: 940

Text #18

Max Range: 5.5547. Min Range: -5.5547

Max Act: 3.6548. Min Act: -0.0000

Data Index: 574847 (The Pile)

Max Activating Token Index: 134

Text #19

Max Range: 5.5547. Min Range: -5.5547

Max Act: 4.1164. Min Act: -0.0000

Data Index: 78155 (The Pile)

Max Activating Token Index: 729