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

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

Neuron 2984 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1736. Min Act: -0.0002

Data Index: 319760 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1640. Min Act: -0.0002

Data Index: 657353 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1637. Min Act: -0.0002

Data Index: 788294 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1581. Min Act: -0.0002

Data Index: 476254 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1577. Min Act: -0.0002

Data Index: 1118164 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1589. Min Act: -0.0002

Data Index: 774444 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1425. Min Act: -0.0002

Data Index: 1259231 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1455. Min Act: -0.0002

Data Index: 942664 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1473. Min Act: -0.0002

Data Index: 1308411 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1348. Min Act: -0.0002

Data Index: 446496 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1308. Min Act: -0.0002

Data Index: 1292405 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1359. Min Act: -0.0002

Data Index: 649888 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1310. Min Act: -0.0002

Data Index: 817487 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1303. Min Act: -0.0002

Data Index: 1354653 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1318. Min Act: -0.0002

Data Index: 788568 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1401. Min Act: -0.0002

Data Index: 250883 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1334. Min Act: -0.0002

Data Index: 1138996 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1388. Min Act: -0.0002

Data Index: 1303486 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1341. Min Act: -0.0002

Data Index: 1202924 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1331. Min Act: -0.0002

Data Index: 1246682 (C4 (Web Text))

Max Activating Token Index: 128