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

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

Neuron 4553 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.4750. Min Act: -0.0000

Data Index: 963795 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3815. Min Act: -0.0000

Data Index: 224258 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3491. Min Act: -0.0000

Data Index: 516561 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3505. Min Act: 0.0000

Data Index: 546035 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3244. Min Act: -0.0000

Data Index: 268723 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3017. Min Act: -0.0000

Data Index: 843579 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.2922. Min Act: -0.0000

Data Index: 1070655 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1162880 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.2680. Min Act: -0.0000

Data Index: 599742 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.2698. Min Act: -0.0000

Data Index: 448683 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.2568. Min Act: -0.0000

Data Index: 769979 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.2633. Min Act: -0.0000

Data Index: 1066222 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.2619. Min Act: 0.0000

Data Index: 1264715 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.2592. Min Act: 0.0000

Data Index: 524316 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.2589. Min Act: 0.0000

Data Index: 1035217 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.2547. Min Act: 0.0000

Data Index: 975765 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.2408. Min Act: -0.0000

Data Index: 1119679 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.2401. Min Act: -0.0000

Data Index: 786021 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.2514. Min Act: -0.0000

Data Index: 207733 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 0.4750. Min Range: -0.4750

Max Act: 0.2381. Min Act: -0.0000

Data Index: 298165 (C4 (Web Text))

Max Activating Token Index: 891