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

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

Neuron 3195 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1619. Min Act: -0.0001

Data Index: 1005032 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1613. Min Act: -0.0001

Data Index: 886943 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1640. Min Act: -0.0001

Data Index: 370262 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1499. Min Act: -0.0001

Data Index: 687087 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1448. Min Act: -0.0001

Data Index: 329867 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1576. Min Act: -0.0001

Data Index: 471058 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1479. Min Act: -0.0001

Data Index: 889242 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1498. Min Act: -0.0001

Data Index: 902914 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1499. Min Act: -0.0001

Data Index: 40495 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1462. Min Act: -0.0001

Data Index: 357299 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1352. Min Act: -0.0001

Data Index: 419760 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1423. Min Act: -0.0001

Data Index: 796923 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1438. Min Act: -0.0001

Data Index: 1095953 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1465. Min Act: -0.0001

Data Index: 1341914 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1419. Min Act: -0.0001

Data Index: 76107 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1418. Min Act: -0.0001

Data Index: 603708 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1403. Min Act: -0.0001

Data Index: 225677 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1449. Min Act: -0.0001

Data Index: 912041 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1370. Min Act: -0.0001

Data Index: 95156 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1329. Min Act: -0.0001

Data Index: 71385 (C4 (Web Text))

Max Activating Token Index: 700