Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3825 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.2401. Min Act: -0.0000

Data Index: 18241 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1804. Min Act: -0.0000

Data Index: 129283 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1692. Min Act: -0.0000

Data Index: 1205606 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1721. Min Act: -0.0000

Data Index: 317928 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1722. Min Act: -0.0000

Data Index: 996303 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1563. Min Act: -0.0000

Data Index: 742312 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1767. Min Act: -0.0000

Data Index: 105993 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1576. Min Act: -0.0000

Data Index: 96202 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1603. Min Act: -0.0000

Data Index: 197955 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1635. Min Act: -0.0000

Data Index: 755186 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1528. Min Act: -0.0000

Data Index: 275719 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1468. Min Act: -0.0000

Data Index: 431127 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1509. Min Act: -0.0000

Data Index: 1239058 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1548. Min Act: -0.0000

Data Index: 84832 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1441. Min Act: -0.0000

Data Index: 173135 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1432. Min Act: -0.0000

Data Index: 632907 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1378. Min Act: -0.0000

Data Index: 643667 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1037894 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1374. Min Act: -0.0000

Data Index: 212395 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.2401. Min Range: -0.2401

Max Act: 0.1418. Min Act: -0.0000

Data Index: 79806 (C4 (Web Text))

Max Activating Token Index: 65