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

Dataset: The Pile

Neuron 1321 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.8569. Min Act: -0.0000

Data Index: 919847 (The Pile)

Max Activating Token Index: 647

Text #1

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.6786. Min Act: -0.0000

Data Index: 1294828 (The Pile)

Max Activating Token Index: 204

Text #2

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.8283. Min Act: -0.0000

Data Index: 858093 (The Pile)

Max Activating Token Index: 789

Text #3

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.5344. Min Act: -0.0000

Data Index: 245318 (The Pile)

Max Activating Token Index: 333

Text #4

Max Range: 5.0474. Min Range: -5.0474

Max Act: 5.0474. Min Act: -0.0000

Data Index: 1711621 (The Pile)

Max Activating Token Index: 168

Text #5

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.6647. Min Act: -0.0000

Data Index: 1090372 (The Pile)

Max Activating Token Index: 901

Text #6

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.6239. Min Act: -0.0000

Data Index: 826115 (The Pile)

Max Activating Token Index: 40

Text #7

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.2231. Min Act: -0.0000

Data Index: 1855488 (The Pile)

Max Activating Token Index: 852

Text #8

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.0501. Min Act: -0.0000

Data Index: 166962 (The Pile)

Max Activating Token Index: 932

Text #9

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.6851. Min Act: -0.0000

Data Index: 1420388 (The Pile)

Max Activating Token Index: 143

Text #10

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.4857. Min Act: -0.0000

Data Index: 814862 (The Pile)

Max Activating Token Index: 899

Text #11

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.0457. Min Act: -0.0000

Data Index: 754829 (The Pile)

Max Activating Token Index: 700

Text #12

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.3323. Min Act: -0.0000

Data Index: 1073598 (The Pile)

Max Activating Token Index: 638

Text #13

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.1209. Min Act: -0.0000

Data Index: 1564397 (The Pile)

Max Activating Token Index: 485

Text #14

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.2568. Min Act: -0.0000

Data Index: 782441 (The Pile)

Max Activating Token Index: 611

Text #15

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.2252. Min Act: -0.0000

Data Index: 500836 (The Pile)

Max Activating Token Index: 948

Text #16

Max Range: 5.0474. Min Range: -5.0474

Max Act: 3.9298. Min Act: -0.0000

Data Index: 1007894 (The Pile)

Max Activating Token Index: 424

Text #17

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.0263. Min Act: -0.0000

Data Index: 1492665 (The Pile)

Max Activating Token Index: 922

Text #18

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.3833. Min Act: -0.0000

Data Index: 1938287 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 5.0474. Min Range: -5.0474

Max Act: 4.3394. Min Act: -0.0000

Data Index: 1576067 (The Pile)

Max Activating Token Index: 920