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

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

Neuron 530 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1580. Min Act: -0.0006

Data Index: 301741 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1523. Min Act: -0.0006

Data Index: 369818 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1538. Min Act: -0.0006

Data Index: 1201918 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1578. Min Act: -0.0006

Data Index: 785389 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1520. Min Act: -0.0006

Data Index: 361028 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1517. Min Act: -0.0006

Data Index: 955429 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1391. Min Act: -0.0006

Data Index: 938966 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1332. Min Act: -0.0006

Data Index: 535329 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1424. Min Act: -0.0006

Data Index: 467331 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1409. Min Act: -0.0006

Data Index: 944838 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1296. Min Act: -0.0006

Data Index: 385928 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1503. Min Act: -0.0006

Data Index: 1133653 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1384. Min Act: -0.0006

Data Index: 66476 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1435. Min Act: -0.0006

Data Index: 1288665 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1383. Min Act: -0.0006

Data Index: 54895 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1375. Min Act: -0.0006

Data Index: 986935 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1313. Min Act: -0.0006

Data Index: 583120 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1412. Min Act: -0.0006

Data Index: 1199074 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1304. Min Act: -0.0006

Data Index: 1242751 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1414. Min Act: -0.0006

Data Index: 581300 (C4 (Web Text))

Max Activating Token Index: 473