Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 620 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1830. Min Act: -0.0002

Data Index: 733662 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1796. Min Act: -0.0002

Data Index: 16918 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1746. Min Act: -0.0002

Data Index: 97898 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1616. Min Act: -0.0002

Data Index: 265627 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1594. Min Act: -0.0002

Data Index: 14614 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1561. Min Act: -0.0002

Data Index: 104245 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1543. Min Act: -0.0002

Data Index: 1331112 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1477. Min Act: -0.0002

Data Index: 111471 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1519. Min Act: -0.0002

Data Index: 499388 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1507. Min Act: -0.0002

Data Index: 1265694 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1521. Min Act: -0.0002

Data Index: 987982 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1478. Min Act: -0.0002

Data Index: 246070 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1463. Min Act: -0.0002

Data Index: 209487 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1435. Min Act: -0.0002

Data Index: 649804 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1445. Min Act: -0.0002

Data Index: 41419 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1401. Min Act: -0.0002

Data Index: 92174 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1456. Min Act: -0.0002

Data Index: 1128238 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1398. Min Act: -0.0002

Data Index: 820739 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1399. Min Act: -0.0002

Data Index: 258638 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.1830. Min Range: -0.1830

Max Act: 0.1445. Min Act: -0.0002

Data Index: 650908 (C4 (Web Text))

Max Activating Token Index: 366