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

Dataset: The Pile

Neuron 1017 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.2996. Min Act: -0.0000

Data Index: 354318 (The Pile)

Max Activating Token Index: 790

Text #1

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.6351. Min Act: -0.0000

Data Index: 1445907 (The Pile)

Max Activating Token Index: 436

Text #2

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.4269. Min Act: -0.0000

Data Index: 523717 (The Pile)

Max Activating Token Index: 786

Text #3

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.2350. Min Act: -0.0000

Data Index: 1011990 (The Pile)

Max Activating Token Index: 701

Text #4

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.2171. Min Act: -0.0000

Data Index: 481036 (The Pile)

Max Activating Token Index: 869

Text #5

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.3934. Min Act: -0.0000

Data Index: 817069 (The Pile)

Max Activating Token Index: 615

Text #6

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.2578. Min Act: -0.0000

Data Index: 1532646 (The Pile)

Max Activating Token Index: 323

Text #7

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.2588. Min Act: -0.0000

Data Index: 1269658 (The Pile)

Max Activating Token Index: 718

Text #8

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.2632. Min Act: -0.0000

Data Index: 1155843 (The Pile)

Max Activating Token Index: 835

Text #9

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.2857. Min Act: -0.0000

Data Index: 1939692 (The Pile)

Max Activating Token Index: 744

Text #10

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.1215. Min Act: -0.0000

Data Index: 1220700 (The Pile)

Max Activating Token Index: 700

Text #11

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.3597. Min Act: -0.0000

Data Index: 1659244 (The Pile)

Max Activating Token Index: 823

Text #12

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.0930. Min Act: -0.0000

Data Index: 1921217 (The Pile)

Max Activating Token Index: 1016

Text #13

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.0447. Min Act: -0.0000

Data Index: 827835 (The Pile)

Max Activating Token Index: 319

Text #14

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.1293. Min Act: -0.0000

Data Index: 1309838 (The Pile)

Max Activating Token Index: 518

Text #15

Max Range: 1.6351. Min Range: -1.6351

Max Act: 0.9987. Min Act: -0.0000

Data Index: 1268722 (The Pile)

Max Activating Token Index: 47

Text #16

Max Range: 1.6351. Min Range: -1.6351

Max Act: 0.9949. Min Act: -0.0000

Data Index: 1378508 (The Pile)

Max Activating Token Index: 396

Text #17

Max Range: 1.6351. Min Range: -1.6351

Max Act: 0.9710. Min Act: -0.0000

Data Index: 144591 (The Pile)

Max Activating Token Index: 474

Text #18

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.0536. Min Act: -0.0000

Data Index: 562596 (The Pile)

Max Activating Token Index: 70

Text #19

Max Range: 1.6351. Min Range: -1.6351

Max Act: 0.9873. Min Act: -0.0000

Data Index: 1677245 (The Pile)

Max Activating Token Index: 269