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

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

Neuron 2517 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1991. Min Act: -0.0001

Data Index: 858692 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1868. Min Act: -0.0001

Data Index: 643882 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1862. Min Act: -0.0001

Data Index: 135510 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1776. Min Act: -0.0001

Data Index: 714268 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1702. Min Act: -0.0001

Data Index: 866178 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1798. Min Act: -0.0001

Data Index: 809858 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1650. Min Act: -0.0001

Data Index: 1245335 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1581. Min Act: -0.0001

Data Index: 373333 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1455. Min Act: -0.0001

Data Index: 1032851 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1468. Min Act: -0.0001

Data Index: 1003989 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1475. Min Act: -0.0001

Data Index: 1286772 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1456. Min Act: -0.0001

Data Index: 1337666 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1331. Min Act: -0.0001

Data Index: 498271 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1309. Min Act: -0.0001

Data Index: 499093 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1375. Min Act: -0.0001

Data Index: 1304085 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1267. Min Act: -0.0001

Data Index: 981190 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1301. Min Act: -0.0001

Data Index: 711559 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1242. Min Act: -0.0001

Data Index: 141795 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1231. Min Act: -0.0001

Data Index: 680968 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.1991. Min Range: -0.1991

Max Act: 0.1275. Min Act: -0.0001

Data Index: 808761 (C4 (Web Text))

Max Activating Token Index: 795