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

Dataset: The Pile

Neuron 3290 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: 1.2450. Min Range: -1.2450

Max Act: 1.2450. Min Act: -0.0000

Data Index: 967146 (The Pile)

Max Activating Token Index: 442

Text #1

Max Range: 1.2450. Min Range: -1.2450

Max Act: 1.2441. Min Act: -0.0000

Data Index: 1654830 (The Pile)

Max Activating Token Index: 15

Text #2

Max Range: 1.2450. Min Range: -1.2450

Max Act: 1.1841. Min Act: -0.0000

Data Index: 252553 (The Pile)

Max Activating Token Index: 20

Text #3

Max Range: 1.2450. Min Range: -1.2450

Max Act: 0.9629. Min Act: -0.0000

Data Index: 445453 (The Pile)

Max Activating Token Index: 531

Text #4

Max Range: 1.2450. Min Range: -1.2450

Max Act: 1.1260. Min Act: -0.0000

Data Index: 916240 (The Pile)

Max Activating Token Index: 202

Text #5

Max Range: 1.2450. Min Range: -1.2450

Max Act: 1.1526. Min Act: -0.0000

Data Index: 970706 (The Pile)

Max Activating Token Index: 197

Text #6

Max Range: 1.2450. Min Range: -1.2450

Max Act: 1.1218. Min Act: -0.0000

Data Index: 723140 (The Pile)

Max Activating Token Index: 202

Text #7

Max Range: 1.2450. Min Range: -1.2450

Max Act: 1.0955. Min Act: -0.0000

Data Index: 556016 (The Pile)

Max Activating Token Index: 213

Text #8

Max Range: 1.2450. Min Range: -1.2450

Max Act: 1.1157. Min Act: -0.0000

Data Index: 1019114 (The Pile)

Max Activating Token Index: 627

Text #9

Max Range: 1.2450. Min Range: -1.2450

Max Act: 1.0013. Min Act: -0.0000

Data Index: 1554637 (The Pile)

Max Activating Token Index: 152

Text #10

Max Range: 1.2450. Min Range: -1.2450

Max Act: 0.9995. Min Act: -0.0000

Data Index: 1541450 (The Pile)

Max Activating Token Index: 620

Text #11

Max Range: 1.2450. Min Range: -1.2450

Max Act: 0.9648. Min Act: -0.0000

Data Index: 1320553 (The Pile)

Max Activating Token Index: 67

Text #12

Max Range: 1.2450. Min Range: -1.2450

Max Act: 1.0458. Min Act: -0.0000

Data Index: 655064 (The Pile)

Max Activating Token Index: 59

Text #13

Max Range: 1.2450. Min Range: -1.2450

Max Act: 0.9395. Min Act: -0.0000

Data Index: 343425 (The Pile)

Max Activating Token Index: 502

Text #14

Max Range: 1.2450. Min Range: -1.2450

Max Act: 1.0401. Min Act: -0.0000

Data Index: 124407 (The Pile)

Max Activating Token Index: 744

Text #15

Max Range: 1.2450. Min Range: -1.2450

Max Act: 0.9869. Min Act: -0.0000

Data Index: 479170 (The Pile)

Max Activating Token Index: 593

Text #16

Max Range: 1.2450. Min Range: -1.2450

Max Act: 0.9710. Min Act: -0.0000

Data Index: 1012298 (The Pile)

Max Activating Token Index: 98

Text #17

Max Range: 1.2450. Min Range: -1.2450

Max Act: 0.9991. Min Act: -0.0001

Data Index: 408975 (The Pile)

Max Activating Token Index: 10

Text #18

Max Range: 1.2450. Min Range: -1.2450

Max Act: 0.9380. Min Act: -0.0000

Data Index: 613366 (The Pile)

Max Activating Token Index: 37

Text #19

Max Range: 1.2450. Min Range: -1.2450

Max Act: 0.8258. Min Act: -0.0000

Data Index: 501554 (The Pile)

Max Activating Token Index: 651