Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1683 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.7665. Min Act: -0.0000

Data Index: 902089 (The Pile)

Max Activating Token Index: 35

Text #1

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.3130. Min Act: -0.0000

Data Index: 64324 (The Pile)

Max Activating Token Index: 922

Text #2

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.2231. Min Act: -0.0000

Data Index: 1788686 (The Pile)

Max Activating Token Index: 871

Text #3

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.2948. Min Act: -0.0000

Data Index: 1408587 (The Pile)

Max Activating Token Index: 550

Text #4

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.1399. Min Act: -0.0000

Data Index: 805843 (The Pile)

Max Activating Token Index: 166

Text #5

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.1371. Min Act: -0.0000

Data Index: 24548 (The Pile)

Max Activating Token Index: 728

Text #6

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.1374. Min Act: -0.0000

Data Index: 1054964 (The Pile)

Max Activating Token Index: 285

Text #7

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.1235. Min Act: -0.0000

Data Index: 912703 (The Pile)

Max Activating Token Index: 449

Text #8

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.0373. Min Act: -0.0000

Data Index: 511429 (The Pile)

Max Activating Token Index: 1018

Text #9

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.1671. Min Act: -0.0000

Data Index: 1668711 (The Pile)

Max Activating Token Index: 447

Text #10

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.0260. Min Act: -0.0000

Data Index: 1135148 (The Pile)

Max Activating Token Index: 275

Text #11

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.0103. Min Act: -0.0000

Data Index: 1287742 (The Pile)

Max Activating Token Index: 364

Text #12

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.0458. Min Act: -0.0000

Data Index: 293362 (The Pile)

Max Activating Token Index: 864

Text #13

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.2816. Min Act: -0.0000

Data Index: 270592 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 1.7665. Min Range: -1.7665

Max Act: 0.9357. Min Act: -0.0000

Data Index: 628445 (The Pile)

Max Activating Token Index: 427

Text #15

Max Range: 1.7665. Min Range: -1.7665

Max Act: 0.8059. Min Act: -0.0000

Data Index: 1412947 (The Pile)

Max Activating Token Index: 1020

Text #16

Max Range: 1.7665. Min Range: -1.7665

Max Act: 0.9034. Min Act: -0.0000

Data Index: 1993814 (The Pile)

Max Activating Token Index: 635

Text #17

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.0251. Min Act: -0.0001

Data Index: 923487 (The Pile)

Max Activating Token Index: 301

Text #18

Max Range: 1.7665. Min Range: -1.7665

Max Act: 1.0531. Min Act: -0.0000

Data Index: 936020 (The Pile)

Max Activating Token Index: 715

Text #19

Max Range: 1.7665. Min Range: -1.7665

Max Act: 0.9679. Min Act: -0.0000

Data Index: 501013 (The Pile)

Max Activating Token Index: 174