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

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

Neuron 3285 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2696. Min Act: -0.0000

Data Index: 102821 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2541. Min Act: -0.0000

Data Index: 1144545 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2210. Min Act: -0.0000

Data Index: 979169 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2057. Min Act: -0.0000

Data Index: 1257200 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1296567 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1842. Min Act: -0.0000

Data Index: 641767 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1796. Min Act: -0.0000

Data Index: 966517 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1679. Min Act: -0.0000

Data Index: 438110 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1746. Min Act: -0.0000

Data Index: 1077007 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1671. Min Act: -0.0000

Data Index: 1156354 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1649. Min Act: -0.0000

Data Index: 992513 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1590. Min Act: -0.0000

Data Index: 550527 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1585. Min Act: -0.0000

Data Index: 976301 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1606. Min Act: -0.0000

Data Index: 16495 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1555. Min Act: -0.0000

Data Index: 1068609 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1587. Min Act: -0.0000

Data Index: 779882 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1612. Min Act: -0.0000

Data Index: 605050 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1556. Min Act: -0.0000

Data Index: 1103497 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1475. Min Act: -0.0000

Data Index: 313528 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.2696. Min Range: -0.2696

Max Act: 0.1443. Min Act: -0.0000

Data Index: 711987 (C4 (Web Text))

Max Activating Token Index: 597