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

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

Neuron 1047 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.7427. Min Act: -0.0000

Data Index: 704416 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.4442. Min Act: -0.0000

Data Index: 751251 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.3249. Min Act: -0.0000

Data Index: 1240016 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.2899. Min Act: -0.0000

Data Index: 901904 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.3733. Min Act: -0.0000

Data Index: 252297 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.2320. Min Act: -0.0000

Data Index: 1094950 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.1589. Min Act: -0.0000

Data Index: 1207592 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.0330. Min Act: -0.0000

Data Index: 1205380 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 2.7427. Min Range: -2.7427

Max Act: 1.9361. Min Act: -0.0000

Data Index: 865419 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.1548. Min Act: -0.0000

Data Index: 1288050 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.0059. Min Act: -0.0000

Data Index: 280544 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.1071. Min Act: -0.0000

Data Index: 180828 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.0825. Min Act: -0.0000

Data Index: 200384 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 2.7427. Min Range: -2.7427

Max Act: 1.9907. Min Act: -0.0000

Data Index: 451172 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.0601. Min Act: -0.0000

Data Index: 595622 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.1997. Min Act: -0.0000

Data Index: 336395 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.0611. Min Act: -0.0000

Data Index: 1238065 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 2.7427. Min Range: -2.7427

Max Act: 1.9749. Min Act: -0.0000

Data Index: 370749 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.1766. Min Act: -0.0000

Data Index: 367977 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 2.7427. Min Range: -2.7427

Max Act: 2.1693. Min Act: -0.0000

Data Index: 248302 (C4 (Web Text))

Max Activating Token Index: 774