Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 220 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1712. Min Act: -0.0003

Data Index: 1476733 (Python Code)

Max Activating Token Index: 454

Text #1

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1353. Min Act: -0.0003

Data Index: 1487063 (Python Code)

Max Activating Token Index: 592

Text #2

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1241. Min Act: -0.0003

Data Index: 1562887 (Python Code)

Max Activating Token Index: 777

Text #3

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1024. Min Act: -0.0003

Data Index: 1624306 (Python Code)

Max Activating Token Index: 889

Text #4

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0783. Min Act: -0.0003

Data Index: 1422031 (Python Code)

Max Activating Token Index: 240

Text #5

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0625. Min Act: -0.0004

Data Index: 626492 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0637. Min Act: -0.0003

Data Index: 1453385 (Python Code)

Max Activating Token Index: 232

Text #7

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0517. Min Act: -0.0003

Data Index: 544127 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0391. Min Act: -0.0004

Data Index: 525375 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0414. Min Act: -0.0003

Data Index: 1524919 (Python Code)

Max Activating Token Index: 536

Text #10

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0359. Min Act: -0.0002

Data Index: 593853 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1613865 (Python Code)

Max Activating Token Index: 343

Text #12

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0333. Min Act: -0.0004

Data Index: 1014414 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1154817 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0345. Min Act: -0.0003

Data Index: 424026 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0342. Min Act: -0.0004

Data Index: 673665 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0319. Min Act: -0.0003

Data Index: 65310 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0324. Min Act: -0.0003

Data Index: 283668 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0319. Min Act: -0.0003

Data Index: 874977 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0329. Min Act: -0.0003

Data Index: 669652 (C4 (Web Text))

Max Activating Token Index: 205