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

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

Neuron 3364 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2336. Min Act: -0.0000

Data Index: 841789 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2357. Min Act: -0.0001

Data Index: 993536 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1823. Min Act: -0.0000

Data Index: 940580 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1893. Min Act: -0.0000

Data Index: 274349 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1635. Min Act: -0.0001

Data Index: 793459 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1566. Min Act: -0.0000

Data Index: 378241 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1575. Min Act: -0.0000

Data Index: 1350069 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1603. Min Act: -0.0000

Data Index: 609278 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1521. Min Act: -0.0000

Data Index: 896431 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1523. Min Act: -0.0000

Data Index: 1052004 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1566. Min Act: -0.0000

Data Index: 276743 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1459. Min Act: -0.0000

Data Index: 926127 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1355. Min Act: -0.0000

Data Index: 15962 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1417. Min Act: -0.0000

Data Index: 1119015 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1511. Min Act: -0.0000

Data Index: 171675 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1491. Min Act: -0.0001

Data Index: 1131905 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1438. Min Act: -0.0000

Data Index: 468935 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1494. Min Act: -0.0000

Data Index: 387122 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1430. Min Act: -0.0000

Data Index: 1066467 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1430. Min Act: -0.0001

Data Index: 798508 (C4 (Web Text))

Max Activating Token Index: 74