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

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

Neuron 1251 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2568. Min Act: -0.0000

Data Index: 1014590 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2170. Min Act: -0.0000

Data Index: 333786 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2104. Min Act: -0.0000

Data Index: 736207 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1819. Min Act: -0.0000

Data Index: 482747 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1928. Min Act: -0.0000

Data Index: 311111 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1740. Min Act: -0.0000

Data Index: 281723 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1655. Min Act: -0.0000

Data Index: 214403 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1596. Min Act: -0.0000

Data Index: 672242 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1055728 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1628. Min Act: -0.0000

Data Index: 771605 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1513. Min Act: -0.0000

Data Index: 872813 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1515. Min Act: -0.0000

Data Index: 1339831 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1600. Min Act: -0.0000

Data Index: 708586 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1241307 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1635. Min Act: -0.0000

Data Index: 918927 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1508. Min Act: -0.0000

Data Index: 592000 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1608. Min Act: -0.0000

Data Index: 848268 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1537. Min Act: -0.0000

Data Index: 921212 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1475. Min Act: -0.0000

Data Index: 1176630 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1442. Min Act: -0.0000

Data Index: 335988 (C4 (Web Text))

Max Activating Token Index: 472