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

Dataset: The Pile

Neuron 3297 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: 1.8255. Min Range: -1.8255

Max Act: 1.8255. Min Act: -0.0000

Data Index: 1570110 (The Pile)

Max Activating Token Index: 480

Text #1

Max Range: 1.8255. Min Range: -1.8255

Max Act: 1.7681. Min Act: -0.0000

Data Index: 1512795 (The Pile)

Max Activating Token Index: 728

Text #2

Max Range: 1.8255. Min Range: -1.8255

Max Act: 1.4941. Min Act: -0.0000

Data Index: 456419 (The Pile)

Max Activating Token Index: 413

Text #3

Max Range: 1.8255. Min Range: -1.8255

Max Act: 1.3008. Min Act: -0.0000

Data Index: 204127 (The Pile)

Max Activating Token Index: 729

Text #4

Max Range: 1.8255. Min Range: -1.8255

Max Act: 1.1620. Min Act: -0.0000

Data Index: 390699 (The Pile)

Max Activating Token Index: 112

Text #5

Max Range: 1.8255. Min Range: -1.8255

Max Act: 1.1639. Min Act: -0.0000

Data Index: 236258 (The Pile)

Max Activating Token Index: 989

Text #6

Max Range: 1.8255. Min Range: -1.8255

Max Act: 1.0860. Min Act: -0.0000

Data Index: 1087180 (The Pile)

Max Activating Token Index: 928

Text #7

Max Range: 1.8255. Min Range: -1.8255

Max Act: 1.1060. Min Act: -0.0000

Data Index: 552989 (The Pile)

Max Activating Token Index: 130

Text #8

Max Range: 1.8255. Min Range: -1.8255

Max Act: 1.0471. Min Act: -0.0000

Data Index: 488764 (The Pile)

Max Activating Token Index: 202

Text #9

Max Range: 1.8255. Min Range: -1.8255

Max Act: 1.0634. Min Act: -0.0000

Data Index: 1041264 (The Pile)

Max Activating Token Index: 110

Text #10

Max Range: 1.8255. Min Range: -1.8255

Max Act: 1.0260. Min Act: -0.0000

Data Index: 1805796 (The Pile)

Max Activating Token Index: 891

Text #11

Max Range: 1.8255. Min Range: -1.8255

Max Act: 1.0259. Min Act: -0.0000

Data Index: 756288 (The Pile)

Max Activating Token Index: 244

Text #12

Max Range: 1.8255. Min Range: -1.8255

Max Act: 1.0193. Min Act: -0.0000

Data Index: 352594 (The Pile)

Max Activating Token Index: 972

Text #13

Max Range: 1.8255. Min Range: -1.8255

Max Act: 0.9117. Min Act: -0.0000

Data Index: 85794 (The Pile)

Max Activating Token Index: 758

Text #14

Max Range: 1.8255. Min Range: -1.8255

Max Act: 0.9983. Min Act: -0.0000

Data Index: 507420 (The Pile)

Max Activating Token Index: 192

Text #15

Max Range: 1.8255. Min Range: -1.8255

Max Act: 0.9937. Min Act: -0.0000

Data Index: 524717 (The Pile)

Max Activating Token Index: 967

Text #16

Max Range: 1.8255. Min Range: -1.8255

Max Act: 0.9441. Min Act: -0.0000

Data Index: 494527 (The Pile)

Max Activating Token Index: 542

Text #17

Max Range: 1.8255. Min Range: -1.8255

Max Act: 0.9174. Min Act: -0.0000

Data Index: 670867 (The Pile)

Max Activating Token Index: 926

Text #18

Max Range: 1.8255. Min Range: -1.8255

Max Act: 0.9886. Min Act: -0.0000

Data Index: 1626893 (The Pile)

Max Activating Token Index: 726

Text #19

Max Range: 1.8255. Min Range: -1.8255

Max Act: 0.8392. Min Act: -0.0000

Data Index: 701198 (The Pile)

Max Activating Token Index: 770