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

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

Neuron 3486 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2384. Min Act: -0.0000

Data Index: 1126493 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1792. Min Act: -0.0000

Data Index: 1037661 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1512. Min Act: -0.0000

Data Index: 89211 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1902. Min Act: -0.0000

Data Index: 230675 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1877. Min Act: -0.0000

Data Index: 407966 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1626. Min Act: -0.0000

Data Index: 898292 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1623. Min Act: -0.0000

Data Index: 905651 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1563. Min Act: -0.0000

Data Index: 1105102 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1478. Min Act: -0.0000

Data Index: 527655 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1627. Min Act: -0.0000

Data Index: 216222 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1565. Min Act: -0.0000

Data Index: 763630 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1450. Min Act: -0.0000

Data Index: 1300005 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1434. Min Act: -0.0000

Data Index: 449898 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1485. Min Act: -0.0000

Data Index: 373050 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1493. Min Act: -0.0000

Data Index: 1079907 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1386. Min Act: -0.0000

Data Index: 883089 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1541. Min Act: -0.0000

Data Index: 783578 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1358. Min Act: -0.0000

Data Index: 1207971 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1352. Min Act: -0.0000

Data Index: 593687 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1343. Min Act: -0.0000

Data Index: 456122 (C4 (Web Text))

Max Activating Token Index: 682