Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 741 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1882. Min Act: -0.0002

Data Index: 852401 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1829. Min Act: -0.0002

Data Index: 967535 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1779. Min Act: -0.0002

Data Index: 188454 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1565. Min Act: -0.0002

Data Index: 307330 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1695. Min Act: -0.0002

Data Index: 12280 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1522. Min Act: -0.0001

Data Index: 754530 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1559. Min Act: -0.0001

Data Index: 179989 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1606. Min Act: -0.0001

Data Index: 285204 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1418. Min Act: -0.0002

Data Index: 76631 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1573. Min Act: -0.0001

Data Index: 696917 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1455. Min Act: -0.0001

Data Index: 199359 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1468. Min Act: -0.0001

Data Index: 1154823 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1265. Min Act: -0.0002

Data Index: 621079 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1364. Min Act: -0.0002

Data Index: 862235 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1525. Min Act: -0.0002

Data Index: 461523 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1502. Min Act: -0.0001

Data Index: 1024636 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1356. Min Act: -0.0001

Data Index: 504319 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1327. Min Act: -0.0002

Data Index: 1256795 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1417. Min Act: -0.0002

Data Index: 180428 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1520. Min Act: -0.0002

Data Index: 35534 (C4 (Web Text))

Max Activating Token Index: 340