Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 583 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1527. Min Act: -0.0005

Data Index: 621668 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1465. Min Act: -0.0005

Data Index: 318419 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1449. Min Act: -0.0005

Data Index: 1296108 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1487. Min Act: -0.0005

Data Index: 1066461 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1399. Min Act: -0.0005

Data Index: 1124127 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1297. Min Act: -0.0005

Data Index: 977389 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1469. Min Act: -0.0004

Data Index: 28851 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1349. Min Act: -0.0005

Data Index: 950397 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1416. Min Act: -0.0005

Data Index: 951160 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1399. Min Act: -0.0004

Data Index: 979359 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1430. Min Act: -0.0004

Data Index: 359315 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1328. Min Act: -0.0005

Data Index: 294511 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1376. Min Act: -0.0005

Data Index: 469625 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1378. Min Act: -0.0004

Data Index: 1288313 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1356. Min Act: -0.0005

Data Index: 872217 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1366. Min Act: -0.0004

Data Index: 756520 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1348. Min Act: -0.0005

Data Index: 106935 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1303. Min Act: -0.0005

Data Index: 347335 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1355. Min Act: -0.0005

Data Index: 882593 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1267. Min Act: -0.0004

Data Index: 1203162 (C4 (Web Text))

Max Activating Token Index: 915