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

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

Neuron 2378 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1727. Min Act: -0.0000

Data Index: 973058 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1710. Min Act: -0.0000

Data Index: 136550 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1676. Min Act: -0.0000

Data Index: 159279 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1561. Min Act: -0.0000

Data Index: 894614 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1543. Min Act: -0.0000

Data Index: 1120994 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1576. Min Act: -0.0001

Data Index: 602907 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1509. Min Act: -0.0000

Data Index: 1028772 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1502. Min Act: -0.0000

Data Index: 1083754 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1539. Min Act: -0.0000

Data Index: 927640 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1386. Min Act: -0.0000

Data Index: 341797 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1527. Min Act: -0.0000

Data Index: 329311 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1472. Min Act: -0.0000

Data Index: 1191690 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1544. Min Act: -0.0000

Data Index: 1327638 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1337. Min Act: -0.0000

Data Index: 1278192 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1440. Min Act: -0.0001

Data Index: 838546 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1389. Min Act: -0.0001

Data Index: 381435 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1427. Min Act: -0.0000

Data Index: 102937 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1475. Min Act: -0.0000

Data Index: 717602 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1380. Min Act: -0.0001

Data Index: 647633 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.1727. Min Range: -0.1727

Max Act: 0.1472. Min Act: -0.0000

Data Index: 1082827 (C4 (Web Text))

Max Activating Token Index: 561