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

Dataset: The Pile

Neuron 20 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.7095. Min Act: -0.0000

Data Index: 1888153 (The Pile)

Max Activating Token Index: 29

Text #1

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.5995. Min Act: -0.0000

Data Index: 1717435 (The Pile)

Max Activating Token Index: 515

Text #2

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.5245. Min Act: -0.0000

Data Index: 1812130 (The Pile)

Max Activating Token Index: 1018

Text #3

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.4899. Min Act: -0.0000

Data Index: 1379783 (The Pile)

Max Activating Token Index: 371

Text #4

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.4460. Min Act: -0.0000

Data Index: 1707268 (The Pile)

Max Activating Token Index: 638

Text #5

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.4572. Min Act: -0.0000

Data Index: 650488 (The Pile)

Max Activating Token Index: 401

Text #6

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1217923 (The Pile)

Max Activating Token Index: 198

Text #7

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.5048. Min Act: -0.0000

Data Index: 848662 (The Pile)

Max Activating Token Index: 982

Text #8

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.4712. Min Act: -0.0000

Data Index: 1521967 (The Pile)

Max Activating Token Index: 1013

Text #9

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.4089. Min Act: -0.0000

Data Index: 437540 (The Pile)

Max Activating Token Index: 857

Text #10

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.4473. Min Act: -0.0000

Data Index: 173072 (The Pile)

Max Activating Token Index: 845

Text #11

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.4030. Min Act: -0.0000

Data Index: 478228 (The Pile)

Max Activating Token Index: 481

Text #12

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.4290. Min Act: -0.0000

Data Index: 696503 (The Pile)

Max Activating Token Index: 645

Text #13

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.3402. Min Act: -0.0000

Data Index: 499979 (The Pile)

Max Activating Token Index: 943

Text #14

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.4079. Min Act: -0.0000

Data Index: 1364980 (The Pile)

Max Activating Token Index: 522

Text #15

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.3833. Min Act: -0.0000

Data Index: 607984 (The Pile)

Max Activating Token Index: 257

Text #16

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.4181. Min Act: -0.0000

Data Index: 1630971 (The Pile)

Max Activating Token Index: 380

Text #17

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.3692. Min Act: -0.0000

Data Index: 411093 (The Pile)

Max Activating Token Index: 888

Text #18

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.4220. Min Act: -0.0000

Data Index: 813575 (The Pile)

Max Activating Token Index: 604

Text #19

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.4373. Min Act: -0.0000

Data Index: 872820 (The Pile)

Max Activating Token Index: 733