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

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

Neuron 3827 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.2589. Min Act: -0.0001

Data Index: 972737 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1806. Min Act: -0.0000

Data Index: 716739 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1762. Min Act: -0.0000

Data Index: 78013 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1731. Min Act: -0.0000

Data Index: 274349 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1005687 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1617. Min Act: -0.0001

Data Index: 1119174 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1626. Min Act: -0.0001

Data Index: 76703 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1572. Min Act: -0.0000

Data Index: 1303644 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1566. Min Act: -0.0000

Data Index: 690941 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1485. Min Act: -0.0000

Data Index: 682720 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1487. Min Act: -0.0000

Data Index: 1298895 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1498. Min Act: -0.0000

Data Index: 404928 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1431. Min Act: -0.0001

Data Index: 1048313 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1426. Min Act: -0.0000

Data Index: 369816 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1265. Min Act: -0.0000

Data Index: 213079 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1413. Min Act: -0.0000

Data Index: 1178911 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1444. Min Act: -0.0000

Data Index: 757804 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1385. Min Act: -0.0000

Data Index: 932572 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1375. Min Act: -0.0000

Data Index: 743015 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 0.2589. Min Range: -0.2589

Max Act: 0.1324. Min Act: -0.0001

Data Index: 1050845 (C4 (Web Text))

Max Activating Token Index: 917