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

Dataset: The Pile

Neuron 1646 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: 1.5588. Min Range: -1.5588

Max Act: 1.5588. Min Act: -0.0000

Data Index: 1970037 (The Pile)

Max Activating Token Index: 755

Text #1

Max Range: 1.5588. Min Range: -1.5588

Max Act: 1.1674. Min Act: -0.0000

Data Index: 747966 (The Pile)

Max Activating Token Index: 67

Text #2

Max Range: 1.5588. Min Range: -1.5588

Max Act: 1.1411. Min Act: -0.0000

Data Index: 878980 (The Pile)

Max Activating Token Index: 815

Text #3

Max Range: 1.5588. Min Range: -1.5588

Max Act: 1.1780. Min Act: -0.0000

Data Index: 50879 (The Pile)

Max Activating Token Index: 308

Text #4

Max Range: 1.5588. Min Range: -1.5588

Max Act: 0.9205. Min Act: -0.0000

Data Index: 1903259 (The Pile)

Max Activating Token Index: 715

Text #5

Max Range: 1.5588. Min Range: -1.5588

Max Act: 0.7728. Min Act: -0.0000

Data Index: 628320 (The Pile)

Max Activating Token Index: 937

Text #6

Max Range: 1.5588. Min Range: -1.5588

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1370777 (The Pile)

Max Activating Token Index: 1008

Text #7

Max Range: 1.5588. Min Range: -1.5588

Max Act: 0.4619. Min Act: -0.0000

Data Index: 504661 (The Pile)

Max Activating Token Index: 485

Text #8

Max Range: 1.5588. Min Range: -1.5588

Max Act: 0.4102. Min Act: -0.0000

Data Index: 1260342 (The Pile)

Max Activating Token Index: 473

Text #9

Max Range: 1.5588. Min Range: -1.5588

Max Act: 0.4241. Min Act: -0.0000

Data Index: 529354 (The Pile)

Max Activating Token Index: 43

Text #10

Max Range: 1.5588. Min Range: -1.5588

Max Act: 0.3756. Min Act: -0.0000

Data Index: 626893 (The Pile)

Max Activating Token Index: 745

Text #11

Max Range: 1.5588. Min Range: -1.5588

Max Act: 0.3714. Min Act: -0.0000

Data Index: 386002 (The Pile)

Max Activating Token Index: 978

Text #12

Max Range: 1.5588. Min Range: -1.5588

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1783296 (The Pile)

Max Activating Token Index: 383

Text #13

Max Range: 1.5588. Min Range: -1.5588

Max Act: 0.3844. Min Act: -0.0000

Data Index: 628010 (The Pile)

Max Activating Token Index: 193

Text #14

Max Range: 1.5588. Min Range: -1.5588

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1626853 (The Pile)

Max Activating Token Index: 977

Text #15

Max Range: 1.5588. Min Range: -1.5588

Max Act: 0.3457. Min Act: -0.0000

Data Index: 1934509 (The Pile)

Max Activating Token Index: 530

Text #16

Max Range: 1.5588. Min Range: -1.5588

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1816340 (The Pile)

Max Activating Token Index: 601

Text #17

Max Range: 1.5588. Min Range: -1.5588

Max Act: 0.3161. Min Act: -0.0000

Data Index: 60485 (The Pile)

Max Activating Token Index: 948

Text #18

Max Range: 1.5588. Min Range: -1.5588

Max Act: 0.3484. Min Act: -0.0000

Data Index: 782805 (The Pile)

Max Activating Token Index: 128

Text #19

Max Range: 1.5588. Min Range: -1.5588

Max Act: 0.3462. Min Act: -0.0000

Data Index: 387670 (The Pile)

Max Activating Token Index: 239