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

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

Neuron 1378 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.2048. Min Act: -0.0001

Data Index: 485703 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1724. Min Act: -0.0001

Data Index: 345515 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1902. Min Act: -0.0001

Data Index: 953597 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1694. Min Act: -0.0001

Data Index: 274274 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1619. Min Act: -0.0001

Data Index: 582197 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1552. Min Act: -0.0001

Data Index: 1294177 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1595. Min Act: -0.0001

Data Index: 845708 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1585. Min Act: -0.0001

Data Index: 1296471 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1547. Min Act: -0.0001

Data Index: 805088 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1566. Min Act: -0.0001

Data Index: 375592 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1506. Min Act: -0.0001

Data Index: 820516 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1475. Min Act: -0.0001

Data Index: 175430 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1527. Min Act: -0.0001

Data Index: 948616 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1518. Min Act: -0.0001

Data Index: 776786 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1487. Min Act: -0.0001

Data Index: 284715 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1523. Min Act: -0.0001

Data Index: 420041 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1458. Min Act: -0.0001

Data Index: 359897 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1461. Min Act: -0.0001

Data Index: 1157454 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1458. Min Act: -0.0001

Data Index: 183788 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1447. Min Act: -0.0001

Data Index: 368747 (C4 (Web Text))

Max Activating Token Index: 443