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

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

Neuron 2847 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1715. Min Act: -0.0001

Data Index: 640166 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1559. Min Act: -0.0001

Data Index: 1501477 (Python Code)

Max Activating Token Index: 181

Text #2

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1657. Min Act: -0.0001

Data Index: 1127825 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1585. Min Act: -0.0001

Data Index: 912985 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1622. Min Act: -0.0001

Data Index: 827149 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1298593 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1632. Min Act: -0.0001

Data Index: 584355 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1628. Min Act: -0.0001

Data Index: 948496 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1622. Min Act: -0.0001

Data Index: 1337019 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1521. Min Act: -0.0001

Data Index: 433254 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1501. Min Act: -0.0001

Data Index: 654619 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1455. Min Act: -0.0001

Data Index: 1296291 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1363. Min Act: -0.0001

Data Index: 677041 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1447. Min Act: -0.0001

Data Index: 45796 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1466. Min Act: -0.0001

Data Index: 15150 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1420. Min Act: -0.0001

Data Index: 728636 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1416. Min Act: -0.0001

Data Index: 71554 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1360. Min Act: -0.0001

Data Index: 735274 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1354. Min Act: -0.0001

Data Index: 703928 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1401. Min Act: -0.0001

Data Index: 960080 (C4 (Web Text))

Max Activating Token Index: 767