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

Dataset: The Pile

Neuron 4811 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0243. Min Range: -1.0243

Max Act: 1.0243. Min Act: -0.0000

Data Index: 1384553 (The Pile)

Max Activating Token Index: 944

Text #1

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8775. Min Act: -0.0000

Data Index: 1384685 (The Pile)

Max Activating Token Index: 943

Text #2

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.9244. Min Act: -0.0000

Data Index: 777908 (The Pile)

Max Activating Token Index: 788

Text #3

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.9273. Min Act: 0.0000

Data Index: 404770 (The Pile)

Max Activating Token Index: 592

Text #4

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8289. Min Act: -0.0000

Data Index: 1264215 (The Pile)

Max Activating Token Index: 285

Text #5

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8758. Min Act: -0.0000

Data Index: 1607774 (The Pile)

Max Activating Token Index: 89

Text #6

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8324. Min Act: -0.0000

Data Index: 1943485 (The Pile)

Max Activating Token Index: 294

Text #7

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7805. Min Act: -0.0000

Data Index: 1674945 (The Pile)

Max Activating Token Index: 838

Text #8

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.6919. Min Act: -0.0000

Data Index: 316386 (The Pile)

Max Activating Token Index: 743

Text #9

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7724. Min Act: -0.0000

Data Index: 818855 (The Pile)

Max Activating Token Index: 743

Text #10

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8030. Min Act: -0.0000

Data Index: 778690 (The Pile)

Max Activating Token Index: 656

Text #11

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.6983. Min Act: -0.0000

Data Index: 491578 (The Pile)

Max Activating Token Index: 993

Text #12

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7700. Min Act: -0.0000

Data Index: 933835 (The Pile)

Max Activating Token Index: 868

Text #13

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.6816. Min Act: -0.0000

Data Index: 273075 (The Pile)

Max Activating Token Index: 1004

Text #14

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1384876 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.6932. Min Act: -0.0000

Data Index: 1056474 (The Pile)

Max Activating Token Index: 451

Text #16

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7665. Min Act: -0.0000

Data Index: 1635945 (The Pile)

Max Activating Token Index: 158

Text #17

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.6618. Min Act: -0.0000

Data Index: 148314 (The Pile)

Max Activating Token Index: 896

Text #18

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1735731 (The Pile)

Max Activating Token Index: 815

Text #19

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.6974. Min Act: -0.0000

Data Index: 638207 (The Pile)

Max Activating Token Index: 600