Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2650 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.2255. Min Act: -0.0001

Data Index: 1048265 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.2129. Min Act: -0.0001

Data Index: 1348894 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1851. Min Act: -0.0001

Data Index: 359231 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1847. Min Act: -0.0001

Data Index: 1075187 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1905. Min Act: -0.0001

Data Index: 164491 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1839. Min Act: -0.0000

Data Index: 541571 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1896. Min Act: -0.0001

Data Index: 1112627 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1864. Min Act: -0.0001

Data Index: 964093 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1840. Min Act: -0.0001

Data Index: 414720 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1770. Min Act: -0.0000

Data Index: 891202 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1872. Min Act: -0.0000

Data Index: 315336 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1683. Min Act: -0.0001

Data Index: 567765 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1793. Min Act: 0.0001

Data Index: 1142119 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1778. Min Act: -0.0001

Data Index: 481011 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1759. Min Act: -0.0001

Data Index: 1123402 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1826. Min Act: -0.0001

Data Index: 590127 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1685. Min Act: -0.0000

Data Index: 320822 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1714. Min Act: -0.0000

Data Index: 267413 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1702. Min Act: -0.0001

Data Index: 1140396 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1664. Min Act: -0.0001

Data Index: 657243 (C4 (Web Text))

Max Activating Token Index: 971