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

Dataset: The Pile

Neuron 1000 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: 1.0448. Min Range: -1.0448

Max Act: 1.0279. Min Act: -0.0000

Data Index: 859175 (The Pile)

Max Activating Token Index: 541

Text #1

Max Range: 1.0448. Min Range: -1.0448

Max Act: 1.0448. Min Act: -0.0000

Data Index: 1680827 (The Pile)

Max Activating Token Index: 422

Text #2

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9816. Min Act: -0.0000

Data Index: 318448 (The Pile)

Max Activating Token Index: 397

Text #3

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9810. Min Act: -0.0000

Data Index: 211335 (The Pile)

Max Activating Token Index: 487

Text #4

Max Range: 1.0448. Min Range: -1.0448

Max Act: 1.0041. Min Act: -0.0000

Data Index: 1613814 (The Pile)

Max Activating Token Index: 987

Text #5

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9131. Min Act: -0.0000

Data Index: 1215430 (The Pile)

Max Activating Token Index: 759

Text #6

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9252. Min Act: -0.0000

Data Index: 1160898 (The Pile)

Max Activating Token Index: 647

Text #7

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9284. Min Act: -0.0000

Data Index: 1465527 (The Pile)

Max Activating Token Index: 1016

Text #8

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1488389 (The Pile)

Max Activating Token Index: 724

Text #9

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8959. Min Act: -0.0000

Data Index: 762664 (The Pile)

Max Activating Token Index: 994

Text #10

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9448. Min Act: -0.0000

Data Index: 421581 (The Pile)

Max Activating Token Index: 753

Text #11

Max Range: 1.0448. Min Range: -1.0448

Max Act: 1.0244. Min Act: -0.0000

Data Index: 1666448 (The Pile)

Max Activating Token Index: 741

Text #12

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9694. Min Act: -0.0000

Data Index: 137293 (The Pile)

Max Activating Token Index: 660

Text #13

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9046. Min Act: -0.0000

Data Index: 1350959 (The Pile)

Max Activating Token Index: 890

Text #14

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8707. Min Act: -0.0000

Data Index: 743628 (The Pile)

Max Activating Token Index: 696

Text #15

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1761241 (The Pile)

Max Activating Token Index: 447

Text #16

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9428. Min Act: -0.0000

Data Index: 795668 (The Pile)

Max Activating Token Index: 817

Text #17

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.9213. Min Act: -0.0000

Data Index: 902127 (The Pile)

Max Activating Token Index: 521

Text #18

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1282304 (The Pile)

Max Activating Token Index: 622

Text #19

Max Range: 1.0448. Min Range: -1.0448

Max Act: 0.8750. Min Act: -0.0000

Data Index: 1481807 (The Pile)

Max Activating Token Index: 791