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

Dataset: The Pile

Neuron 1664 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9615. Min Range: -1.9615

Max Act: 1.9615. Min Act: 0.0000

Data Index: 401115 (The Pile)

Max Activating Token Index: 1015

Text #1

Max Range: 1.9615. Min Range: -1.9615

Max Act: 1.5201. Min Act: 0.0000

Data Index: 1679295 (The Pile)

Max Activating Token Index: 760

Text #2

Max Range: 1.9615. Min Range: -1.9615

Max Act: 1.5611. Min Act: 0.0000

Data Index: 1488503 (The Pile)

Max Activating Token Index: 622

Text #3

Max Range: 1.9615. Min Range: -1.9615

Max Act: 1.4627. Min Act: 0.0000

Data Index: 164427 (The Pile)

Max Activating Token Index: 368

Text #4

Max Range: 1.9615. Min Range: -1.9615

Max Act: 1.3667. Min Act: 0.0000

Data Index: 1802709 (The Pile)

Max Activating Token Index: 594

Text #5

Max Range: 1.9615. Min Range: -1.9615

Max Act: 1.3289. Min Act: -0.0000

Data Index: 764386 (The Pile)

Max Activating Token Index: 622

Text #6

Max Range: 1.9615. Min Range: -1.9615

Max Act: 1.5302. Min Act: -0.0000

Data Index: 1939808 (The Pile)

Max Activating Token Index: 811

Text #7

Max Range: 1.9615. Min Range: -1.9615

Max Act: 1.2726. Min Act: -0.0000

Data Index: 823954 (The Pile)

Max Activating Token Index: 478

Text #8

Max Range: 1.9615. Min Range: -1.9615

Max Act: 1.2135. Min Act: -0.0000

Data Index: 1006928 (The Pile)

Max Activating Token Index: 246

Text #9

Max Range: 1.9615. Min Range: -1.9615

Max Act: 1.1334. Min Act: -0.0000

Data Index: 667331 (The Pile)

Max Activating Token Index: 875

Text #10

Max Range: 1.9615. Min Range: -1.9615

Max Act: 1.1105. Min Act: -0.0000

Data Index: 331125 (The Pile)

Max Activating Token Index: 506

Text #11

Max Range: 1.9615. Min Range: -1.9615

Max Act: 0.9911. Min Act: -0.0000

Data Index: 141935 (The Pile)

Max Activating Token Index: 416

Text #12

Max Range: 1.9615. Min Range: -1.9615

Max Act: 0.9938. Min Act: -0.0000

Data Index: 1520240 (The Pile)

Max Activating Token Index: 515

Text #13

Max Range: 1.9615. Min Range: -1.9615

Max Act: 1.1590. Min Act: 0.0000

Data Index: 406401 (The Pile)

Max Activating Token Index: 327

Text #14

Max Range: 1.9615. Min Range: -1.9615

Max Act: 1.0466. Min Act: -0.0000

Data Index: 552827 (The Pile)

Max Activating Token Index: 867

Text #15

Max Range: 1.9615. Min Range: -1.9615

Max Act: 0.9912. Min Act: 0.0000

Data Index: 501451 (The Pile)

Max Activating Token Index: 278

Text #16

Max Range: 1.9615. Min Range: -1.9615

Max Act: 0.9339. Min Act: -0.0000

Data Index: 1888702 (The Pile)

Max Activating Token Index: 1011

Text #17

Max Range: 1.9615. Min Range: -1.9615

Max Act: 0.9531. Min Act: -0.0000

Data Index: 665396 (The Pile)

Max Activating Token Index: 936

Text #18

Max Range: 1.9615. Min Range: -1.9615

Max Act: 0.9742. Min Act: 0.0000

Data Index: 528889 (The Pile)

Max Activating Token Index: 425

Text #19

Max Range: 1.9615. Min Range: -1.9615

Max Act: 1.0265. Min Act: -0.0000

Data Index: 859241 (The Pile)

Max Activating Token Index: 748