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

Dataset: The Pile

Neuron 4376 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: 5.8478. Min Range: -5.8478

Max Act: 5.7151. Min Act: -0.0000

Data Index: 1970349 (The Pile)

Max Activating Token Index: 943

Text #1

Max Range: 5.8478. Min Range: -5.8478

Max Act: 5.8478. Min Act: -0.0000

Data Index: 1227295 (The Pile)

Max Activating Token Index: 548

Text #2

Max Range: 5.8478. Min Range: -5.8478

Max Act: 5.4533. Min Act: -0.0000

Data Index: 1350193 (The Pile)

Max Activating Token Index: 943

Text #3

Max Range: 5.8478. Min Range: -5.8478

Max Act: 5.4534. Min Act: -0.0000

Data Index: 364766 (The Pile)

Max Activating Token Index: 548

Text #4

Max Range: 5.8478. Min Range: -5.8478

Max Act: 5.2257. Min Act: -0.0000

Data Index: 1349143 (The Pile)

Max Activating Token Index: 761

Text #5

Max Range: 5.8478. Min Range: -5.8478

Max Act: 5.3854. Min Act: -0.0000

Data Index: 1560290 (The Pile)

Max Activating Token Index: 429

Text #6

Max Range: 5.8478. Min Range: -5.8478

Max Act: 5.2866. Min Act: -0.0000

Data Index: 811560 (The Pile)

Max Activating Token Index: 959

Text #7

Max Range: 5.8478. Min Range: -5.8478

Max Act: 5.2806. Min Act: -0.0000

Data Index: 1586372 (The Pile)

Max Activating Token Index: 967

Text #8

Max Range: 5.8478. Min Range: -5.8478

Max Act: 5.7187. Min Act: -0.0000

Data Index: 461609 (The Pile)

Max Activating Token Index: 784

Text #9

Max Range: 5.8478. Min Range: -5.8478

Max Act: 5.2898. Min Act: -0.0000

Data Index: 554136 (The Pile)

Max Activating Token Index: 851

Text #10

Max Range: 5.8478. Min Range: -5.8478

Max Act: 5.2661. Min Act: -0.0000

Data Index: 1950116 (The Pile)

Max Activating Token Index: 727

Text #11

Max Range: 5.8478. Min Range: -5.8478

Max Act: 5.0604. Min Act: -0.0000

Data Index: 570806 (The Pile)

Max Activating Token Index: 978

Text #12

Max Range: 5.8478. Min Range: -5.8478

Max Act: 5.2440. Min Act: -0.0000

Data Index: 579579 (The Pile)

Max Activating Token Index: 484

Text #13

Max Range: 5.8478. Min Range: -5.8478

Max Act: 5.2311. Min Act: -0.0000

Data Index: 134155 (The Pile)

Max Activating Token Index: 779

Text #14

Max Range: 5.8478. Min Range: -5.8478

Max Act: 5.2136. Min Act: -0.0000

Data Index: 1724329 (The Pile)

Max Activating Token Index: 622

Text #15

Max Range: 5.8478. Min Range: -5.8478

Max Act: 5.1669. Min Act: -0.0000

Data Index: 1695349 (The Pile)

Max Activating Token Index: 620

Text #16

Max Range: 5.8478. Min Range: -5.8478

Max Act: 5.2171. Min Act: -0.0000

Data Index: 1649882 (The Pile)

Max Activating Token Index: 639

Text #17

Max Range: 5.8478. Min Range: -5.8478

Max Act: 5.2909. Min Act: -0.0000

Data Index: 1054374 (The Pile)

Max Activating Token Index: 1020

Text #18

Max Range: 5.8478. Min Range: -5.8478

Max Act: 5.2455. Min Act: -0.0000

Data Index: 1046932 (The Pile)

Max Activating Token Index: 802

Text #19

Max Range: 5.8478. Min Range: -5.8478

Max Act: 5.0438. Min Act: -0.0000

Data Index: 1074592 (The Pile)

Max Activating Token Index: 801