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

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

Neuron 3477 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: 0.1662. Min Range: -0.1662

Max Act: 0.1532. Min Act: -0.0002

Data Index: 1312446 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1662. Min Act: -0.0002

Data Index: 13469 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1594. Min Act: -0.0002

Data Index: 979913 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1512. Min Act: -0.0002

Data Index: 501248 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1494. Min Act: -0.0002

Data Index: 1290961 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1547. Min Act: -0.0002

Data Index: 289877 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1636. Min Act: -0.0002

Data Index: 386083 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1496. Min Act: -0.0002

Data Index: 365185 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1635. Min Act: -0.0002

Data Index: 380590 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1483. Min Act: -0.0002

Data Index: 29390 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1444. Min Act: -0.0002

Data Index: 406726 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1292. Min Act: -0.0002

Data Index: 662399 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1638. Min Act: -0.0002

Data Index: 380186 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1521. Min Act: -0.0002

Data Index: 897386 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1380. Min Act: -0.0002

Data Index: 1186116 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1513. Min Act: -0.0002

Data Index: 556196 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1615. Min Act: -0.0002

Data Index: 1278885 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1415. Min Act: -0.0002

Data Index: 1328962 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1318. Min Act: -0.0002

Data Index: 323157 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1304. Min Act: -0.0002

Data Index: 280506 (C4 (Web Text))

Max Activating Token Index: 238