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

Dataset: The Pile

Neuron 2669 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: 1.9662. Min Range: -1.9662

Max Act: 1.9662. Min Act: -0.0000

Data Index: 1761557 (The Pile)

Max Activating Token Index: 743

Text #1

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.7604. Min Act: -0.0000

Data Index: 1053710 (The Pile)

Max Activating Token Index: 788

Text #2

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.5414. Min Act: -0.0000

Data Index: 339712 (The Pile)

Max Activating Token Index: 638

Text #3

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.5437. Min Act: -0.0000

Data Index: 1771181 (The Pile)

Max Activating Token Index: 348

Text #4

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.4967. Min Act: -0.0000

Data Index: 765687 (The Pile)

Max Activating Token Index: 243

Text #5

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.5527. Min Act: -0.0000

Data Index: 1828890 (The Pile)

Max Activating Token Index: 922

Text #6

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.4388. Min Act: -0.0000

Data Index: 17239 (The Pile)

Max Activating Token Index: 200

Text #7

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.3895. Min Act: -0.0000

Data Index: 85514 (The Pile)

Max Activating Token Index: 663

Text #8

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.4626. Min Act: -0.0000

Data Index: 1310926 (The Pile)

Max Activating Token Index: 896

Text #9

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.5990. Min Act: -0.0000

Data Index: 26858 (The Pile)

Max Activating Token Index: 624

Text #10

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.4400. Min Act: -0.0000

Data Index: 1348580 (The Pile)

Max Activating Token Index: 367

Text #11

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.4014. Min Act: -0.0000

Data Index: 1441275 (The Pile)

Max Activating Token Index: 513

Text #12

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.4399. Min Act: -0.0000

Data Index: 1894326 (The Pile)

Max Activating Token Index: 198

Text #13

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.4703. Min Act: -0.0000

Data Index: 881556 (The Pile)

Max Activating Token Index: 391

Text #14

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.4213. Min Act: -0.0000

Data Index: 1252100 (The Pile)

Max Activating Token Index: 596

Text #15

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.4201. Min Act: -0.0000

Data Index: 1190643 (The Pile)

Max Activating Token Index: 836

Text #16

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.4445. Min Act: -0.0000

Data Index: 1073032 (The Pile)

Max Activating Token Index: 969

Text #17

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.3819. Min Act: -0.0000

Data Index: 1608894 (The Pile)

Max Activating Token Index: 346

Text #18

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.3977. Min Act: -0.0000

Data Index: 652954 (The Pile)

Max Activating Token Index: 900

Text #19

Max Range: 1.9662. Min Range: -1.9662

Max Act: 1.3798. Min Act: -0.0000

Data Index: 306279 (The Pile)

Max Activating Token Index: 788