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

Dataset: The Pile

Neuron 3284 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.8434. Min Act: -0.0000

Data Index: 487983 (The Pile)

Max Activating Token Index: 352

Text #1

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.7425. Min Act: -0.0000

Data Index: 1488874 (The Pile)

Max Activating Token Index: 140

Text #2

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.7476. Min Act: -0.0000

Data Index: 1721943 (The Pile)

Max Activating Token Index: 333

Text #3

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6715. Min Act: -0.0000

Data Index: 1816494 (The Pile)

Max Activating Token Index: 569

Text #4

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6848. Min Act: -0.0000

Data Index: 716112 (The Pile)

Max Activating Token Index: 113

Text #5

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.7051. Min Act: -0.0000

Data Index: 490348 (The Pile)

Max Activating Token Index: 346

Text #6

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6867. Min Act: -0.0000

Data Index: 901915 (The Pile)

Max Activating Token Index: 533

Text #7

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1390519 (The Pile)

Max Activating Token Index: 28

Text #8

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6864. Min Act: -0.0000

Data Index: 866733 (The Pile)

Max Activating Token Index: 861

Text #9

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6594. Min Act: -0.0000

Data Index: 289929 (The Pile)

Max Activating Token Index: 15

Text #10

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6718. Min Act: -0.0000

Data Index: 948412 (The Pile)

Max Activating Token Index: 274

Text #11

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6420. Min Act: -0.0000

Data Index: 341571 (The Pile)

Max Activating Token Index: 175

Text #12

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6537. Min Act: -0.0000

Data Index: 514403 (The Pile)

Max Activating Token Index: 195

Text #13

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6579. Min Act: -0.0000

Data Index: 1272352 (The Pile)

Max Activating Token Index: 357

Text #14

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6191. Min Act: -0.0000

Data Index: 1413217 (The Pile)

Max Activating Token Index: 51

Text #15

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1633252 (The Pile)

Max Activating Token Index: 922

Text #16

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.5966. Min Act: -0.0000

Data Index: 182328 (The Pile)

Max Activating Token Index: 210

Text #17

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6154. Min Act: -0.0000

Data Index: 1808541 (The Pile)

Max Activating Token Index: 713

Text #18

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.5926. Min Act: -0.0000

Data Index: 1394287 (The Pile)

Max Activating Token Index: 17

Text #19

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6115. Min Act: -0.0000

Data Index: 587066 (The Pile)

Max Activating Token Index: 14