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

Dataset: The Pile

Neuron 885 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.5795. Min Act: -0.0000

Data Index: 77926 (The Pile)

Max Activating Token Index: 618

Text #1

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.2115. Min Act: -0.0000

Data Index: 898163 (The Pile)

Max Activating Token Index: 865

Text #2

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.2797. Min Act: -0.0000

Data Index: 174736 (The Pile)

Max Activating Token Index: 899

Text #3

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.2610. Min Act: -0.0000

Data Index: 891534 (The Pile)

Max Activating Token Index: 952

Text #4

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.2164. Min Act: -0.0000

Data Index: 587880 (The Pile)

Max Activating Token Index: 281

Text #5

Max Range: 1.5795. Min Range: -1.5795

Max Act: 0.9654. Min Act: -0.0000

Data Index: 943186 (The Pile)

Max Activating Token Index: 1004

Text #6

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.0982. Min Act: -0.0000

Data Index: 606752 (The Pile)

Max Activating Token Index: 958

Text #7

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.1535. Min Act: -0.0000

Data Index: 1515277 (The Pile)

Max Activating Token Index: 508

Text #8

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.0600. Min Act: -0.0000

Data Index: 154331 (The Pile)

Max Activating Token Index: 239

Text #9

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.0855. Min Act: -0.0000

Data Index: 1818200 (The Pile)

Max Activating Token Index: 98

Text #10

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.0155. Min Act: -0.0000

Data Index: 274165 (The Pile)

Max Activating Token Index: 211

Text #11

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.1328. Min Act: -0.0000

Data Index: 682319 (The Pile)

Max Activating Token Index: 661

Text #12

Max Range: 1.5795. Min Range: -1.5795

Max Act: 0.9916. Min Act: -0.0000

Data Index: 1476570 (The Pile)

Max Activating Token Index: 175

Text #13

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.0061. Min Act: -0.0000

Data Index: 1391163 (The Pile)

Max Activating Token Index: 822

Text #14

Max Range: 1.5795. Min Range: -1.5795

Max Act: 0.9951. Min Act: -0.0000

Data Index: 1087855 (The Pile)

Max Activating Token Index: 716

Text #15

Max Range: 1.5795. Min Range: -1.5795

Max Act: 0.9923. Min Act: -0.0000

Data Index: 811087 (The Pile)

Max Activating Token Index: 245

Text #16

Max Range: 1.5795. Min Range: -1.5795

Max Act: 0.9906. Min Act: -0.0000

Data Index: 1542896 (The Pile)

Max Activating Token Index: 1012

Text #17

Max Range: 1.5795. Min Range: -1.5795

Max Act: 0.9119. Min Act: 0.0000

Data Index: 115374 (The Pile)

Max Activating Token Index: 92

Text #18

Max Range: 1.5795. Min Range: -1.5795

Max Act: 0.9545. Min Act: -0.0000

Data Index: 1979212 (The Pile)

Max Activating Token Index: 764

Text #19

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.0125. Min Act: -0.0000

Data Index: 238158 (The Pile)

Max Activating Token Index: 90