Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1689 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1734. Min Act: -0.0001

Data Index: 988213 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1703. Min Act: -0.0001

Data Index: 826843 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1721. Min Act: -0.0000

Data Index: 982429 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1515. Min Act: -0.0001

Data Index: 802378 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1526. Min Act: -0.0001

Data Index: 1153096 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1503. Min Act: -0.0000

Data Index: 529166 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1602. Min Act: -0.0001

Data Index: 51409 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1494. Min Act: -0.0001

Data Index: 1310695 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1547. Min Act: -0.0001

Data Index: 117648 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1429. Min Act: -0.0000

Data Index: 26551 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1563. Min Act: -0.0001

Data Index: 704437 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1447. Min Act: -0.0001

Data Index: 120657 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1441. Min Act: -0.0001

Data Index: 459894 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1440. Min Act: -0.0000

Data Index: 214940 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1353. Min Act: -0.0001

Data Index: 83892 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1387. Min Act: -0.0001

Data Index: 452436 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1334. Min Act: -0.0001

Data Index: 455338 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1370. Min Act: -0.0000

Data Index: 234839 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1380. Min Act: -0.0001

Data Index: 547754 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1374. Min Act: -0.0001

Data Index: 511402 (C4 (Web Text))

Max Activating Token Index: 123