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

Dataset: The Pile

Neuron 3599 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: 0.7965. Min Range: -0.7965

Max Act: 0.7965. Min Act: -0.0000

Data Index: 648784 (The Pile)

Max Activating Token Index: 691

Text #1

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6519. Min Act: -0.0000

Data Index: 1709746 (The Pile)

Max Activating Token Index: 902

Text #2

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6397. Min Act: -0.0000

Data Index: 314677 (The Pile)

Max Activating Token Index: 494

Text #3

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1550148 (The Pile)

Max Activating Token Index: 808

Text #4

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6136. Min Act: -0.0000

Data Index: 1269439 (The Pile)

Max Activating Token Index: 816

Text #5

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6019. Min Act: -0.0000

Data Index: 1347181 (The Pile)

Max Activating Token Index: 815

Text #6

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1667391 (The Pile)

Max Activating Token Index: 432

Text #7

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6010. Min Act: -0.0000

Data Index: 358330 (The Pile)

Max Activating Token Index: 87

Text #8

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.5607. Min Act: -0.0000

Data Index: 1141922 (The Pile)

Max Activating Token Index: 592

Text #9

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6028. Min Act: -0.0000

Data Index: 334005 (The Pile)

Max Activating Token Index: 944

Text #10

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.5919. Min Act: -0.0000

Data Index: 1230492 (The Pile)

Max Activating Token Index: 187

Text #11

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.5527. Min Act: -0.0000

Data Index: 908564 (The Pile)

Max Activating Token Index: 269

Text #12

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.5115. Min Act: -0.0000

Data Index: 1883141 (The Pile)

Max Activating Token Index: 102

Text #13

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.6253. Min Act: -0.0000

Data Index: 120002 (The Pile)

Max Activating Token Index: 545

Text #14

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.5261. Min Act: -0.0000

Data Index: 14707 (The Pile)

Max Activating Token Index: 574

Text #15

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.5731. Min Act: -0.0000

Data Index: 400921 (The Pile)

Max Activating Token Index: 26

Text #16

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.5256. Min Act: -0.0000

Data Index: 857977 (The Pile)

Max Activating Token Index: 332

Text #17

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.5126. Min Act: -0.0000

Data Index: 1052294 (The Pile)

Max Activating Token Index: 506

Text #18

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.5408. Min Act: -0.0000

Data Index: 1615410 (The Pile)

Max Activating Token Index: 197

Text #19

Max Range: 0.7965. Min Range: -0.7965

Max Act: 0.5230. Min Act: -0.0000

Data Index: 873129 (The Pile)

Max Activating Token Index: 432