Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1385 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.2299. Min Act: -0.0001

Data Index: 1267660 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1769. Min Act: -0.0001

Data Index: 848416 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1611. Min Act: -0.0001

Data Index: 1350493 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1700. Min Act: -0.0001

Data Index: 1317730 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1553. Min Act: -0.0001

Data Index: 885228 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1656. Min Act: -0.0001

Data Index: 20619 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1639. Min Act: -0.0001

Data Index: 629505 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1503. Min Act: -0.0001

Data Index: 379067 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1647. Min Act: -0.0001

Data Index: 3360 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1522. Min Act: -0.0001

Data Index: 314189 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1642. Min Act: -0.0001

Data Index: 507177 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1589. Min Act: -0.0001

Data Index: 212501 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1579. Min Act: -0.0001

Data Index: 214206 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1397. Min Act: -0.0001

Data Index: 515274 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1622. Min Act: -0.0001

Data Index: 1035901 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1390. Min Act: -0.0001

Data Index: 1030584 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1481. Min Act: -0.0001

Data Index: 868530 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1477. Min Act: -0.0001

Data Index: 1173397 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1590. Min Act: -0.0001

Data Index: 104180 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1455. Min Act: -0.0001

Data Index: 1194057 (C4 (Web Text))

Max Activating Token Index: 923