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

Dataset: The Pile

Neuron 2244 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1805173 (The Pile)

Max Activating Token Index: 626

Text #1

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6391. Min Act: -0.0000

Data Index: 639018 (The Pile)

Max Activating Token Index: 133

Text #2

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6570. Min Act: -0.0000

Data Index: 732318 (The Pile)

Max Activating Token Index: 432

Text #3

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1094450 (The Pile)

Max Activating Token Index: 247

Text #4

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5910. Min Act: -0.0000

Data Index: 1171761 (The Pile)

Max Activating Token Index: 467

Text #5

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5476. Min Act: -0.0000

Data Index: 1522818 (The Pile)

Max Activating Token Index: 805

Text #6

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5634. Min Act: -0.0000

Data Index: 1318792 (The Pile)

Max Activating Token Index: 586

Text #7

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5867. Min Act: -0.0000

Data Index: 616038 (The Pile)

Max Activating Token Index: 372

Text #8

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5322. Min Act: -0.0000

Data Index: 1193926 (The Pile)

Max Activating Token Index: 620

Text #9

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5786. Min Act: -0.0000

Data Index: 174666 (The Pile)

Max Activating Token Index: 17

Text #10

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5741. Min Act: -0.0000

Data Index: 12404 (The Pile)

Max Activating Token Index: 589

Text #11

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1736947 (The Pile)

Max Activating Token Index: 29

Text #12

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5586. Min Act: -0.0000

Data Index: 919017 (The Pile)

Max Activating Token Index: 209

Text #13

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5585. Min Act: -0.0000

Data Index: 1727540 (The Pile)

Max Activating Token Index: 208

Text #14

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5339. Min Act: -0.0000

Data Index: 114788 (The Pile)

Max Activating Token Index: 200

Text #15

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5152. Min Act: -0.0000

Data Index: 1972998 (The Pile)

Max Activating Token Index: 233

Text #16

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5332. Min Act: -0.0000

Data Index: 207158 (The Pile)

Max Activating Token Index: 839

Text #17

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5187. Min Act: -0.0000

Data Index: 1540112 (The Pile)

Max Activating Token Index: 966

Text #18

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5259. Min Act: -0.0000

Data Index: 1359920 (The Pile)

Max Activating Token Index: 252

Text #19

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5833. Min Act: -0.0000

Data Index: 918966 (The Pile)

Max Activating Token Index: 746