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

Dataset: The Pile

Neuron 2007 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: 1.9882. Min Range: -1.9882

Max Act: 1.9882. Min Act: -0.0000

Data Index: 602073 (The Pile)

Max Activating Token Index: 957

Text #1

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.9127. Min Act: -0.0000

Data Index: 58782 (The Pile)

Max Activating Token Index: 987

Text #2

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.7478. Min Act: -0.0000

Data Index: 495989 (The Pile)

Max Activating Token Index: 838

Text #3

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.8601. Min Act: -0.0000

Data Index: 455244 (The Pile)

Max Activating Token Index: 786

Text #4

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.8211. Min Act: -0.0000

Data Index: 1614102 (The Pile)

Max Activating Token Index: 920

Text #5

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.6676. Min Act: -0.0000

Data Index: 1061442 (The Pile)

Max Activating Token Index: 955

Text #6

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.4720. Min Act: -0.0000

Data Index: 363971 (The Pile)

Max Activating Token Index: 958

Text #7

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.5243. Min Act: -0.0000

Data Index: 1121304 (The Pile)

Max Activating Token Index: 587

Text #8

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.5248. Min Act: -0.0000

Data Index: 1951904 (The Pile)

Max Activating Token Index: 609

Text #9

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.7170. Min Act: -0.0000

Data Index: 1289276 (The Pile)

Max Activating Token Index: 704

Text #10

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.6745. Min Act: -0.0000

Data Index: 318975 (The Pile)

Max Activating Token Index: 1003

Text #11

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.5964. Min Act: -0.0000

Data Index: 409062 (The Pile)

Max Activating Token Index: 913

Text #12

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.4736. Min Act: -0.0000

Data Index: 876567 (The Pile)

Max Activating Token Index: 576

Text #13

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.4097. Min Act: -0.0000

Data Index: 89516 (The Pile)

Max Activating Token Index: 1011

Text #14

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.4462. Min Act: -0.0000

Data Index: 1438132 (The Pile)

Max Activating Token Index: 173

Text #15

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.5254. Min Act: -0.0000

Data Index: 1080211 (The Pile)

Max Activating Token Index: 180

Text #16

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.4195. Min Act: -0.0000

Data Index: 933942 (The Pile)

Max Activating Token Index: 838

Text #17

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.3208. Min Act: -0.0000

Data Index: 282771 (The Pile)

Max Activating Token Index: 183

Text #18

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.5163. Min Act: -0.0000

Data Index: 1192664 (The Pile)

Max Activating Token Index: 817

Text #19

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.4881. Min Act: -0.0000

Data Index: 639776 (The Pile)

Max Activating Token Index: 596