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

Dataset: The Pile

Neuron 4001 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: 0.1800. Min Range: -0.1800

Max Act: 0.1800. Min Act: -0.0000

Data Index: 820307 (The Pile)

Max Activating Token Index: 331

Text #1

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1517. Min Act: -0.0000

Data Index: 1155981 (The Pile)

Max Activating Token Index: 733

Text #2

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1621. Min Act: -0.0000

Data Index: 940301 (The Pile)

Max Activating Token Index: 923

Text #3

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1621. Min Act: -0.0000

Data Index: 875025 (The Pile)

Max Activating Token Index: 961

Text #4

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1423. Min Act: -0.0000

Data Index: 224358 (The Pile)

Max Activating Token Index: 233

Text #5

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1563. Min Act: -0.0000

Data Index: 1512115 (The Pile)

Max Activating Token Index: 863

Text #6

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1485. Min Act: -0.0000

Data Index: 934091 (The Pile)

Max Activating Token Index: 615

Text #7

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1519. Min Act: -0.0000

Data Index: 741225 (The Pile)

Max Activating Token Index: 186

Text #8

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1516. Min Act: -0.0000

Data Index: 497733 (The Pile)

Max Activating Token Index: 664

Text #9

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1477. Min Act: -0.0000

Data Index: 384565 (The Pile)

Max Activating Token Index: 299

Text #10

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1396. Min Act: -0.0000

Data Index: 1463239 (The Pile)

Max Activating Token Index: 735

Text #11

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1228. Min Act: -0.0000

Data Index: 435143 (The Pile)

Max Activating Token Index: 645

Text #12

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1325. Min Act: -0.0000

Data Index: 533237 (The Pile)

Max Activating Token Index: 212

Text #13

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1270. Min Act: -0.0000

Data Index: 1861673 (The Pile)

Max Activating Token Index: 388

Text #14

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1156. Min Act: -0.0000

Data Index: 1803520 (The Pile)

Max Activating Token Index: 135

Text #15

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1149. Min Act: -0.0000

Data Index: 809771 (The Pile)

Max Activating Token Index: 371

Text #16

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1229. Min Act: -0.0000

Data Index: 945347 (The Pile)

Max Activating Token Index: 825

Text #17

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1224. Min Act: -0.0000

Data Index: 57798 (The Pile)

Max Activating Token Index: 157

Text #18

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1196. Min Act: -0.0000

Data Index: 1146932 (The Pile)

Max Activating Token Index: 982

Text #19

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1057. Min Act: -0.0000

Data Index: 290900 (The Pile)

Max Activating Token Index: 735