Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4155 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1054642 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0608. Min Act: -0.0002

Data Index: 569642 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0531. Min Act: -0.0002

Data Index: 715595 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0484. Min Act: -0.0002

Data Index: 777608 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1185776 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0541. Min Act: -0.0002

Data Index: 307611 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0508. Min Act: -0.0002

Data Index: 779268 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0441. Min Act: -0.0002

Data Index: 930022 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0462. Min Act: -0.0002

Data Index: 386719 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0464. Min Act: -0.0002

Data Index: 15693 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0451. Min Act: -0.0002

Data Index: 218555 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0445. Min Act: -0.0002

Data Index: 717740 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0440. Min Act: -0.0002

Data Index: 341159 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1006067 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1196342 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0447. Min Act: -0.0002

Data Index: 927478 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0443. Min Act: -0.0002

Data Index: 502607 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0405. Min Act: -0.0002

Data Index: 431564 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0424. Min Act: -0.0002

Data Index: 438953 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0412. Min Act: -0.0002

Data Index: 624970 (C4 (Web Text))

Max Activating Token Index: 993