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

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

Neuron 1489 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1831. Min Act: -0.0000

Data Index: 358569 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1786. Min Act: -0.0001

Data Index: 652132 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1902. Min Act: -0.0001

Data Index: 1266603 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1654. Min Act: -0.0000

Data Index: 258275 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1639. Min Act: -0.0000

Data Index: 1262361 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1596. Min Act: -0.0001

Data Index: 1128429 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1581. Min Act: -0.0000

Data Index: 276865 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1391. Min Act: -0.0001

Data Index: 927558 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1456. Min Act: -0.0000

Data Index: 920603 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1496. Min Act: -0.0001

Data Index: 732527 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1535. Min Act: -0.0000

Data Index: 796952 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1429. Min Act: -0.0000

Data Index: 660612 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1454. Min Act: -0.0001

Data Index: 842314 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1604. Min Act: -0.0000

Data Index: 1223072 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1471. Min Act: -0.0000

Data Index: 1089018 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1491. Min Act: -0.0000

Data Index: 501009 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1405. Min Act: -0.0001

Data Index: 224788 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1419. Min Act: -0.0000

Data Index: 60524 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1499. Min Act: -0.0000

Data Index: 1353181 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 0.1902. Min Range: -0.1902

Max Act: 0.1393. Min Act: -0.0000

Data Index: 1085499 (C4 (Web Text))

Max Activating Token Index: 741