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

Dataset: The Pile

Neuron 2990 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: 0.5726. Min Range: -0.5726

Max Act: 0.5726. Min Act: -0.0000

Data Index: 1690913 (The Pile)

Max Activating Token Index: 331

Text #1

Max Range: 0.5726. Min Range: -0.5726

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1636686 (The Pile)

Max Activating Token Index: 821

Text #2

Max Range: 0.5726. Min Range: -0.5726

Max Act: 0.5399. Min Act: -0.0000

Data Index: 166770 (The Pile)

Max Activating Token Index: 709

Text #3

Max Range: 0.5726. Min Range: -0.5726

Max Act: 0.5190. Min Act: -0.0000

Data Index: 1328634 (The Pile)

Max Activating Token Index: 49

Text #4

Max Range: 0.5726. Min Range: -0.5726

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1301984 (The Pile)

Max Activating Token Index: 635

Text #5

Max Range: 0.5726. Min Range: -0.5726

Max Act: 0.4675. Min Act: -0.0000

Data Index: 1235476 (The Pile)

Max Activating Token Index: 78

Text #6

Max Range: 0.5726. Min Range: -0.5726

Max Act: 0.4689. Min Act: 0.0000

Data Index: 1450427 (The Pile)

Max Activating Token Index: 215

Text #7

Max Range: 0.5726. Min Range: -0.5726

Max Act: 0.4607. Min Act: -0.0000

Data Index: 730816 (The Pile)

Max Activating Token Index: 199

Text #8

Max Range: 0.5726. Min Range: -0.5726

Max Act: 0.4730. Min Act: -0.0000

Data Index: 714066 (The Pile)

Max Activating Token Index: 288

Text #9

Max Range: 0.5726. Min Range: -0.5726

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1956698 (The Pile)

Max Activating Token Index: 870

Text #10

Max Range: 0.5726. Min Range: -0.5726

Max Act: 0.4601. Min Act: -0.0000

Data Index: 301103 (The Pile)

Max Activating Token Index: 790

Text #11

Max Range: 0.5726. Min Range: -0.5726

Max Act: 0.4376. Min Act: -0.0000

Data Index: 1357549 (The Pile)

Max Activating Token Index: 924

Text #12

Max Range: 0.5726. Min Range: -0.5726

Max Act: 0.4427. Min Act: -0.0000

Data Index: 1012962 (The Pile)

Max Activating Token Index: 143

Text #13

Max Range: 0.5726. Min Range: -0.5726

Max Act: 0.4406. Min Act: -0.0000

Data Index: 815626 (The Pile)

Max Activating Token Index: 256

Text #14

Max Range: 0.5726. Min Range: -0.5726

Max Act: 0.4297. Min Act: -0.0000

Data Index: 689071 (The Pile)

Max Activating Token Index: 371

Text #15

Max Range: 0.5726. Min Range: -0.5726

Max Act: 0.4271. Min Act: -0.0000

Data Index: 378196 (The Pile)

Max Activating Token Index: 23

Text #16

Max Range: 0.5726. Min Range: -0.5726

Max Act: 0.4010. Min Act: -0.0000

Data Index: 1205801 (The Pile)

Max Activating Token Index: 603

Text #17

Max Range: 0.5726. Min Range: -0.5726

Max Act: 0.4239. Min Act: -0.0000

Data Index: 685019 (The Pile)

Max Activating Token Index: 866

Text #18

Max Range: 0.5726. Min Range: -0.5726

Max Act: 0.4257. Min Act: -0.0000

Data Index: 576926 (The Pile)

Max Activating Token Index: 287

Text #19

Max Range: 0.5726. Min Range: -0.5726

Max Act: 0.4240. Min Act: -0.0000

Data Index: 1881981 (The Pile)

Max Activating Token Index: 418