Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5350 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.2404. Min Act: -0.0000

Data Index: 204332 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1003350 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1810. Min Act: -0.0000

Data Index: 744573 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1727. Min Act: -0.0000

Data Index: 178122 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1681. Min Act: -0.0000

Data Index: 907733 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1646. Min Act: -0.0000

Data Index: 338637 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1532. Min Act: -0.0000

Data Index: 740030 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1492. Min Act: -0.0000

Data Index: 104760 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1492. Min Act: -0.0000

Data Index: 1138749 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1504. Min Act: -0.0000

Data Index: 1342437 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1453. Min Act: -0.0000

Data Index: 452452 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1435. Min Act: -0.0000

Data Index: 1152579 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1471. Min Act: -0.0000

Data Index: 1115026 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1521. Min Act: -0.0000

Data Index: 565666 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1365. Min Act: -0.0000

Data Index: 1239555 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1405. Min Act: -0.0000

Data Index: 916510 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1433. Min Act: -0.0000

Data Index: 270631 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1334. Min Act: -0.0000

Data Index: 281762 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1287. Min Act: -0.0000

Data Index: 12229 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 0.2404. Min Range: -0.2404

Max Act: 0.1270. Min Act: -0.0000

Data Index: 2494 (C4 (Web Text))

Max Activating Token Index: 300