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

Dataset: The Pile

Neuron 896 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7420. Min Range: -4.7420

Max Act: 4.7420. Min Act: -0.0000

Data Index: 376112 (The Pile)

Max Activating Token Index: 267

Text #1

Max Range: 4.7420. Min Range: -4.7420

Max Act: 3.7919. Min Act: -0.0000

Data Index: 301469 (The Pile)

Max Activating Token Index: 795

Text #2

Max Range: 4.7420. Min Range: -4.7420

Max Act: 4.5850. Min Act: -0.0000

Data Index: 1558243 (The Pile)

Max Activating Token Index: 231

Text #3

Max Range: 4.7420. Min Range: -4.7420

Max Act: 4.4140. Min Act: -0.0000

Data Index: 236875 (The Pile)

Max Activating Token Index: 902

Text #4

Max Range: 4.7420. Min Range: -4.7420

Max Act: 4.1895. Min Act: -0.0000

Data Index: 987632 (The Pile)

Max Activating Token Index: 887

Text #5

Max Range: 4.7420. Min Range: -4.7420

Max Act: 4.1953. Min Act: -0.0000

Data Index: 509715 (The Pile)

Max Activating Token Index: 556

Text #6

Max Range: 4.7420. Min Range: -4.7420

Max Act: 3.9561. Min Act: -0.0000

Data Index: 380338 (The Pile)

Max Activating Token Index: 313

Text #7

Max Range: 4.7420. Min Range: -4.7420

Max Act: 3.9156. Min Act: -0.0000

Data Index: 1515883 (The Pile)

Max Activating Token Index: 259

Text #8

Max Range: 4.7420. Min Range: -4.7420

Max Act: 3.7690. Min Act: -0.0000

Data Index: 741292 (The Pile)

Max Activating Token Index: 693

Text #9

Max Range: 4.7420. Min Range: -4.7420

Max Act: 4.0187. Min Act: -0.0000

Data Index: 1974806 (The Pile)

Max Activating Token Index: 653

Text #10

Max Range: 4.7420. Min Range: -4.7420

Max Act: 3.8562. Min Act: -0.0000

Data Index: 1349542 (The Pile)

Max Activating Token Index: 516

Text #11

Max Range: 4.7420. Min Range: -4.7420

Max Act: 3.8472. Min Act: -0.0000

Data Index: 1258799 (The Pile)

Max Activating Token Index: 169

Text #12

Max Range: 4.7420. Min Range: -4.7420

Max Act: 4.1616. Min Act: -0.0000

Data Index: 1370103 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 4.7420. Min Range: -4.7420

Max Act: 3.8053. Min Act: -0.0000

Data Index: 958282 (The Pile)

Max Activating Token Index: 680

Text #14

Max Range: 4.7420. Min Range: -4.7420

Max Act: 3.9834. Min Act: -0.0000

Data Index: 386990 (The Pile)

Max Activating Token Index: 304

Text #15

Max Range: 4.7420. Min Range: -4.7420

Max Act: 3.7896. Min Act: -0.0000

Data Index: 1697116 (The Pile)

Max Activating Token Index: 860

Text #16

Max Range: 4.7420. Min Range: -4.7420

Max Act: 3.7879. Min Act: -0.0000

Data Index: 238487 (The Pile)

Max Activating Token Index: 937

Text #17

Max Range: 4.7420. Min Range: -4.7420

Max Act: 3.9161. Min Act: -0.0000

Data Index: 42674 (The Pile)

Max Activating Token Index: 463

Text #18

Max Range: 4.7420. Min Range: -4.7420

Max Act: 3.6439. Min Act: -0.0000

Data Index: 798293 (The Pile)

Max Activating Token Index: 21

Text #19

Max Range: 4.7420. Min Range: -4.7420

Max Act: 3.6183. Min Act: -0.0000

Data Index: 540452 (The Pile)

Max Activating Token Index: 21