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

Dataset: The Pile

Neuron 2047 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.4972. Min Act: -0.0000

Data Index: 421633 (The Pile)

Max Activating Token Index: 977

Text #1

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.4086. Min Act: -0.0000

Data Index: 277804 (The Pile)

Max Activating Token Index: 924

Text #2

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.2297. Min Act: -0.0000

Data Index: 592059 (The Pile)

Max Activating Token Index: 1000

Text #3

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.2196. Min Act: -0.0000

Data Index: 1986442 (The Pile)

Max Activating Token Index: 958

Text #4

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.2690. Min Act: -0.0000

Data Index: 1492286 (The Pile)

Max Activating Token Index: 813

Text #5

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.4829. Min Act: -0.0000

Data Index: 1296426 (The Pile)

Max Activating Token Index: 217

Text #6

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.2547. Min Act: -0.0000

Data Index: 1353236 (The Pile)

Max Activating Token Index: 346

Text #7

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.2673. Min Act: -0.0000

Data Index: 1858932 (The Pile)

Max Activating Token Index: 734

Text #8

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.1652. Min Act: -0.0000

Data Index: 1389173 (The Pile)

Max Activating Token Index: 849

Text #9

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.0328. Min Act: -0.0000

Data Index: 1986355 (The Pile)

Max Activating Token Index: 898

Text #10

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.1040. Min Act: -0.0000

Data Index: 1602481 (The Pile)

Max Activating Token Index: 482

Text #11

Max Range: 1.4972. Min Range: -1.4972

Max Act: 0.9803. Min Act: -0.0000

Data Index: 1251390 (The Pile)

Max Activating Token Index: 841

Text #12

Max Range: 1.4972. Min Range: -1.4972

Max Act: 0.9753. Min Act: -0.0000

Data Index: 1418265 (The Pile)

Max Activating Token Index: 986

Text #13

Max Range: 1.4972. Min Range: -1.4972

Max Act: 0.9912. Min Act: -0.0000

Data Index: 1379967 (The Pile)

Max Activating Token Index: 659

Text #14

Max Range: 1.4972. Min Range: -1.4972

Max Act: 0.9260. Min Act: -0.0000

Data Index: 1213562 (The Pile)

Max Activating Token Index: 923

Text #15

Max Range: 1.4972. Min Range: -1.4972

Max Act: 0.9820. Min Act: -0.0000

Data Index: 963789 (The Pile)

Max Activating Token Index: 1003

Text #16

Max Range: 1.4972. Min Range: -1.4972

Max Act: 0.9773. Min Act: -0.0000

Data Index: 899665 (The Pile)

Max Activating Token Index: 947

Text #17

Max Range: 1.4972. Min Range: -1.4972

Max Act: 0.7857. Min Act: -0.0000

Data Index: 3695 (The Pile)

Max Activating Token Index: 627

Text #18

Max Range: 1.4972. Min Range: -1.4972

Max Act: 0.9088. Min Act: -0.0000

Data Index: 148115 (The Pile)

Max Activating Token Index: 812

Text #19

Max Range: 1.4972. Min Range: -1.4972

Max Act: 0.9031. Min Act: -0.0000

Data Index: 865406 (The Pile)

Max Activating Token Index: 170