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

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

Neuron 3160 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2364. Min Act: -0.0001

Data Index: 281757 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2172. Min Act: -0.0001

Data Index: 73677 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2153. Min Act: -0.0001

Data Index: 806072 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2009. Min Act: -0.0001

Data Index: 647473 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2078. Min Act: -0.0001

Data Index: 1334716 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2030. Min Act: -0.0001

Data Index: 236918 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1984. Min Act: -0.0001

Data Index: 514314 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1606. Min Act: -0.0001

Data Index: 781361 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1794. Min Act: -0.0001

Data Index: 1236643 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1833. Min Act: -0.0001

Data Index: 1347102 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1763. Min Act: -0.0001

Data Index: 70034 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1776. Min Act: -0.0001

Data Index: 598774 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1782. Min Act: -0.0001

Data Index: 1044076 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1779. Min Act: -0.0001

Data Index: 867416 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1832. Min Act: -0.0001

Data Index: 355309 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1542. Min Act: -0.0001

Data Index: 86760 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1804. Min Act: -0.0001

Data Index: 468695 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1739. Min Act: -0.0001

Data Index: 453089 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1577. Min Act: -0.0001

Data Index: 978937 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1698. Min Act: -0.0001

Data Index: 744811 (C4 (Web Text))

Max Activating Token Index: 903