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

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

Neuron 2290 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: 0.5558. Min Range: -0.5558

Max Act: 0.5558. Min Act: -0.0001

Data Index: 1512511 (Python Code)

Max Activating Token Index: 458

Text #1

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4746. Min Act: -0.0001

Data Index: 25529 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4509. Min Act: -0.0001

Data Index: 1646066 (Python Code)

Max Activating Token Index: 391

Text #3

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4376. Min Act: -0.0000

Data Index: 1459093 (Python Code)

Max Activating Token Index: 697

Text #4

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4727. Min Act: -0.0000

Data Index: 1540861 (Python Code)

Max Activating Token Index: 473

Text #5

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4470. Min Act: -0.0000

Data Index: 1526027 (Python Code)

Max Activating Token Index: 425

Text #6

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4672. Min Act: -0.0001

Data Index: 1239962 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4642. Min Act: -0.0000

Data Index: 1564903 (Python Code)

Max Activating Token Index: 585

Text #8

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4663. Min Act: -0.0001

Data Index: 1390830 (Python Code)

Max Activating Token Index: 779

Text #9

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4183. Min Act: -0.0001

Data Index: 1449912 (Python Code)

Max Activating Token Index: 324

Text #10

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4572. Min Act: -0.0001

Data Index: 1627848 (Python Code)

Max Activating Token Index: 510

Text #11

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4732. Min Act: -0.0000

Data Index: 1494630 (Python Code)

Max Activating Token Index: 460

Text #12

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4494. Min Act: -0.0001

Data Index: 477539 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4198. Min Act: -0.0001

Data Index: 1605155 (Python Code)

Max Activating Token Index: 54

Text #14

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4203. Min Act: -0.0001

Data Index: 542280 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.3666. Min Act: -0.0001

Data Index: 766546 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4455. Min Act: -0.0001

Data Index: 1429918 (Python Code)

Max Activating Token Index: 893

Text #17

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4241. Min Act: -0.0001

Data Index: 1525028 (Python Code)

Max Activating Token Index: 897

Text #18

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4246. Min Act: -0.0001

Data Index: 1398828 (Python Code)

Max Activating Token Index: 961

Text #19

Max Range: 0.5558. Min Range: -0.5558

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1385442 (Python Code)

Max Activating Token Index: 579