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

Dataset: The Pile

Neuron 2029 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: 0.9612. Min Range: -0.9612

Max Act: 0.9612. Min Act: -0.0000

Data Index: 1035965 (The Pile)

Max Activating Token Index: 458

Text #1

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.7481. Min Act: -0.0000

Data Index: 88847 (The Pile)

Max Activating Token Index: 196

Text #2

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.8446. Min Act: -0.0000

Data Index: 300779 (The Pile)

Max Activating Token Index: 809

Text #3

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.8430. Min Act: -0.0000

Data Index: 1116205 (The Pile)

Max Activating Token Index: 264

Text #4

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.8615. Min Act: -0.0000

Data Index: 1907219 (The Pile)

Max Activating Token Index: 884

Text #5

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.7917. Min Act: -0.0000

Data Index: 1878407 (The Pile)

Max Activating Token Index: 187

Text #6

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.8085. Min Act: -0.0000

Data Index: 93097 (The Pile)

Max Activating Token Index: 936

Text #7

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.7738. Min Act: -0.0000

Data Index: 1230936 (The Pile)

Max Activating Token Index: 859

Text #8

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.7997. Min Act: -0.0000

Data Index: 1409042 (The Pile)

Max Activating Token Index: 508

Text #9

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.7155. Min Act: -0.0000

Data Index: 63235 (The Pile)

Max Activating Token Index: 895

Text #10

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.7777. Min Act: -0.0000

Data Index: 1106511 (The Pile)

Max Activating Token Index: 253

Text #11

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.7957. Min Act: -0.0000

Data Index: 90219 (The Pile)

Max Activating Token Index: 292

Text #12

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.7196. Min Act: -0.0000

Data Index: 864304 (The Pile)

Max Activating Token Index: 948

Text #13

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1697985 (The Pile)

Max Activating Token Index: 724

Text #14

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.7149. Min Act: -0.0000

Data Index: 888883 (The Pile)

Max Activating Token Index: 166

Text #15

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.6168. Min Act: -0.0000

Data Index: 1694665 (The Pile)

Max Activating Token Index: 1002

Text #16

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.6974. Min Act: -0.0000

Data Index: 1140857 (The Pile)

Max Activating Token Index: 450

Text #17

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.6259. Min Act: -0.0000

Data Index: 1495991 (The Pile)

Max Activating Token Index: 749

Text #18

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.6054. Min Act: -0.0000

Data Index: 57649 (The Pile)

Max Activating Token Index: 989

Text #19

Max Range: 0.9612. Min Range: -0.9612

Max Act: 0.6618. Min Act: -0.0000

Data Index: 271336 (The Pile)

Max Activating Token Index: 440