Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3189 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.9830. Min Act: -0.0001

Data Index: 1181486 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.9139. Min Act: -0.0001

Data Index: 980533 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.9165. Min Act: -0.0001

Data Index: 138525 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.8667. Min Act: -0.0002

Data Index: 703560 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.8200. Min Act: -0.0001

Data Index: 1280606 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.8926. Min Act: -0.0002

Data Index: 328605 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.8631. Min Act: -0.0001

Data Index: 582993 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.8299. Min Act: -0.0001

Data Index: 1265015 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.8175. Min Act: -0.0001

Data Index: 1623618 (Python Code)

Max Activating Token Index: 168

Text #9

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.8405. Min Act: -0.0001

Data Index: 113681 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.8204. Min Act: -0.0001

Data Index: 587937 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.7325. Min Act: -0.0002

Data Index: 742851 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.8285. Min Act: -0.0002

Data Index: 1001137 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.7995. Min Act: -0.0002

Data Index: 1044149 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.7829. Min Act: -0.0001

Data Index: 1030816 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.7777. Min Act: -0.0001

Data Index: 1291229 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.7510. Min Act: -0.0002

Data Index: 861524 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.7918. Min Act: -0.0002

Data Index: 1017314 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.7930. Min Act: -0.0002

Data Index: 990657 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.9830. Min Range: -0.9830

Max Act: 0.7601. Min Act: -0.0002

Data Index: 128589 (C4 (Web Text))

Max Activating Token Index: 299