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

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

Neuron 3913 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3664. Min Range: -0.3664

Max Act: 0.3664. Min Act: -0.0000

Data Index: 107205 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 0.3664. Min Range: -0.3664

Max Act: 0.2433. Min Act: -0.0000

Data Index: 1465022 (Python Code)

Max Activating Token Index: 848

Text #2

Max Range: 0.3664. Min Range: -0.3664

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1314329 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.3664. Min Range: -0.3664

Max Act: 0.2152. Min Act: -0.0000

Data Index: 751565 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 0.3664. Min Range: -0.3664

Max Act: 0.2252. Min Act: -0.0000

Data Index: 309194 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 0.3664. Min Range: -0.3664

Max Act: 0.1865. Min Act: -0.0000

Data Index: 880037 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.3664. Min Range: -0.3664

Max Act: 0.1895. Min Act: -0.0000

Data Index: 1339227 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.3664. Min Range: -0.3664

Max Act: 0.1891. Min Act: -0.0000

Data Index: 592169 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.3664. Min Range: -0.3664

Max Act: 0.1870. Min Act: -0.0000

Data Index: 1328535 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 0.3664. Min Range: -0.3664

Max Act: 0.1843. Min Act: -0.0000

Data Index: 632304 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 0.3664. Min Range: -0.3664

Max Act: 0.1809. Min Act: -0.0000

Data Index: 205879 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 0.3664. Min Range: -0.3664

Max Act: 0.1895. Min Act: -0.0000

Data Index: 1161787 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.3664. Min Range: -0.3664

Max Act: 0.1813. Min Act: -0.0000

Data Index: 113987 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 0.3664. Min Range: -0.3664

Max Act: 0.1740. Min Act: -0.0000

Data Index: 517900 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 0.3664. Min Range: -0.3664

Max Act: 0.1725. Min Act: -0.0000

Data Index: 1287471 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.3664. Min Range: -0.3664

Max Act: 0.1772. Min Act: -0.0000

Data Index: 1168165 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.3664. Min Range: -0.3664

Max Act: 0.1714. Min Act: -0.0000

Data Index: 263900 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 0.3664. Min Range: -0.3664

Max Act: 0.1777. Min Act: -0.0000

Data Index: 204549 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.3664. Min Range: -0.3664

Max Act: 0.1700. Min Act: -0.0000

Data Index: 1090175 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.3664. Min Range: -0.3664

Max Act: 0.1592. Min Act: -0.0000

Data Index: 1068840 (C4 (Web Text))

Max Activating Token Index: 809