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

Dataset: The Pile

Neuron 4620 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: 1.8894. Min Range: -1.8894

Max Act: 1.8894. Min Act: -0.0000

Data Index: 505915 (The Pile)

Max Activating Token Index: 811

Text #1

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.3394. Min Act: -0.0000

Data Index: 39110 (The Pile)

Max Activating Token Index: 1013

Text #2

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.1995. Min Act: -0.0000

Data Index: 1573805 (The Pile)

Max Activating Token Index: 599

Text #3

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.1287. Min Act: -0.0000

Data Index: 290803 (The Pile)

Max Activating Token Index: 611

Text #4

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.1814. Min Act: -0.0000

Data Index: 180599 (The Pile)

Max Activating Token Index: 214

Text #5

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.0908. Min Act: -0.0000

Data Index: 128837 (The Pile)

Max Activating Token Index: 644

Text #6

Max Range: 1.8894. Min Range: -1.8894

Max Act: 0.9828. Min Act: -0.0000

Data Index: 1339855 (The Pile)

Max Activating Token Index: 859

Text #7

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.1177. Min Act: -0.0000

Data Index: 1898020 (The Pile)

Max Activating Token Index: 290

Text #8

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.1585. Min Act: -0.0000

Data Index: 1621462 (The Pile)

Max Activating Token Index: 926

Text #9

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.0756. Min Act: -0.0000

Data Index: 3700 (The Pile)

Max Activating Token Index: 701

Text #10

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.0714. Min Act: -0.0000

Data Index: 730063 (The Pile)

Max Activating Token Index: 274

Text #11

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.0717. Min Act: -0.0000

Data Index: 293689 (The Pile)

Max Activating Token Index: 134

Text #12

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.1341. Min Act: -0.0000

Data Index: 1964853 (The Pile)

Max Activating Token Index: 941

Text #13

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.1195. Min Act: -0.0000

Data Index: 1986289 (The Pile)

Max Activating Token Index: 896

Text #14

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.0442. Min Act: -0.0000

Data Index: 1742786 (The Pile)

Max Activating Token Index: 45

Text #15

Max Range: 1.8894. Min Range: -1.8894

Max Act: 0.9705. Min Act: -0.0000

Data Index: 817202 (The Pile)

Max Activating Token Index: 496

Text #16

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.0626. Min Act: -0.0000

Data Index: 8857 (The Pile)

Max Activating Token Index: 1001

Text #17

Max Range: 1.8894. Min Range: -1.8894

Max Act: 0.9651. Min Act: -0.0000

Data Index: 197757 (The Pile)

Max Activating Token Index: 173

Text #18

Max Range: 1.8894. Min Range: -1.8894

Max Act: 1.0272. Min Act: -0.0000

Data Index: 353078 (The Pile)

Max Activating Token Index: 420

Text #19

Max Range: 1.8894. Min Range: -1.8894

Max Act: 0.9534. Min Act: -0.0000

Data Index: 1488503 (The Pile)

Max Activating Token Index: 514