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

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

Neuron 2026 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: 0.1553. Min Range: -0.1553

Max Act: 0.1553. Min Act: -0.0005

Data Index: 1026412 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1510. Min Act: -0.0005

Data Index: 68904 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1496. Min Act: -0.0005

Data Index: 575606 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1486. Min Act: -0.0005

Data Index: 1293039 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1467. Min Act: -0.0005

Data Index: 1128178 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1501. Min Act: -0.0005

Data Index: 633224 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1437. Min Act: -0.0005

Data Index: 402789 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1438. Min Act: -0.0005

Data Index: 1173424 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1444. Min Act: -0.0005

Data Index: 1172831 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1422. Min Act: -0.0005

Data Index: 579335 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1434. Min Act: -0.0005

Data Index: 736319 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1396. Min Act: -0.0005

Data Index: 1265148 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1402. Min Act: -0.0005

Data Index: 149691 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1394. Min Act: -0.0005

Data Index: 80761 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1387. Min Act: -0.0005

Data Index: 662085 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1386. Min Act: -0.0005

Data Index: 684693 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1239. Min Act: -0.0005

Data Index: 582444 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1365. Min Act: -0.0005

Data Index: 610055 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1221. Min Act: -0.0005

Data Index: 1355807 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1362. Min Act: -0.0005

Data Index: 308822 (C4 (Web Text))

Max Activating Token Index: 19