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

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

Neuron 2858 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: 0.1658. Min Range: -0.1658

Max Act: 0.1605. Min Act: -0.0001

Data Index: 1183563 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1658. Min Act: -0.0001

Data Index: 1226674 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1636. Min Act: -0.0001

Data Index: 5503 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1536. Min Act: -0.0001

Data Index: 493789 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1580. Min Act: -0.0001

Data Index: 44856 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1494. Min Act: -0.0001

Data Index: 961629 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1489. Min Act: -0.0001

Data Index: 507123 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1406. Min Act: -0.0001

Data Index: 200381 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1391. Min Act: -0.0001

Data Index: 340590 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1446. Min Act: -0.0001

Data Index: 330483 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1391. Min Act: -0.0001

Data Index: 85935 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1548. Min Act: -0.0001

Data Index: 610820 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1381. Min Act: -0.0001

Data Index: 1154618 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1368. Min Act: -0.0001

Data Index: 563913 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1374. Min Act: -0.0001

Data Index: 1339541 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1354. Min Act: -0.0001

Data Index: 164460 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1359. Min Act: -0.0001

Data Index: 71336 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1453. Min Act: -0.0001

Data Index: 687483 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1334. Min Act: -0.0001

Data Index: 661023 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.1658. Min Range: -0.1658

Max Act: 0.1381. Min Act: -0.0001

Data Index: 310788 (C4 (Web Text))

Max Activating Token Index: 22