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

Dataset: The Pile

Neuron 931 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1485. Min Range: -4.1485

Max Act: 4.1485. Min Act: -0.0000

Data Index: 968647 (The Pile)

Max Activating Token Index: 190

Text #1

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.3847. Min Act: -0.0000

Data Index: 421605 (The Pile)

Max Activating Token Index: 446

Text #2

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.4356. Min Act: -0.0000

Data Index: 1214555 (The Pile)

Max Activating Token Index: 599

Text #3

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.2009. Min Act: -0.0000

Data Index: 6734 (The Pile)

Max Activating Token Index: 451

Text #4

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.2118. Min Act: -0.0000

Data Index: 274896 (The Pile)

Max Activating Token Index: 474

Text #5

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.0225. Min Act: -0.0000

Data Index: 897252 (The Pile)

Max Activating Token Index: 393

Text #6

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.1519. Min Act: -0.0000

Data Index: 1455765 (The Pile)

Max Activating Token Index: 734

Text #7

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.1218. Min Act: -0.0000

Data Index: 564784 (The Pile)

Max Activating Token Index: 651

Text #8

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.2427. Min Act: -0.0000

Data Index: 829456 (The Pile)

Max Activating Token Index: 475

Text #9

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.2449. Min Act: -0.0000

Data Index: 620188 (The Pile)

Max Activating Token Index: 457

Text #10

Max Range: 4.1485. Min Range: -4.1485

Max Act: 2.9317. Min Act: -0.0000

Data Index: 593909 (The Pile)

Max Activating Token Index: 184

Text #11

Max Range: 4.1485. Min Range: -4.1485

Max Act: 2.9276. Min Act: -0.0000

Data Index: 1480095 (The Pile)

Max Activating Token Index: 266

Text #12

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.5400. Min Act: -0.0000

Data Index: 672863 (The Pile)

Max Activating Token Index: 468

Text #13

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.0642. Min Act: -0.0000

Data Index: 172655 (The Pile)

Max Activating Token Index: 651

Text #14

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.1381. Min Act: -0.0000

Data Index: 314740 (The Pile)

Max Activating Token Index: 466

Text #15

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.0692. Min Act: -0.0000

Data Index: 1737486 (The Pile)

Max Activating Token Index: 422

Text #16

Max Range: 4.1485. Min Range: -4.1485

Max Act: 2.9252. Min Act: -0.0000

Data Index: 260454 (The Pile)

Max Activating Token Index: 666

Text #17

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.0677. Min Act: -0.0000

Data Index: 1597890 (The Pile)

Max Activating Token Index: 804

Text #18

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.0170. Min Act: -0.0000

Data Index: 1699734 (The Pile)

Max Activating Token Index: 272

Text #19

Max Range: 4.1485. Min Range: -4.1485

Max Act: 3.1338. Min Act: -0.0000

Data Index: 1744287 (The Pile)

Max Activating Token Index: 591