Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3384 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1200. Min Range: -1.1200

Max Act: 1.1200. Min Act: -0.0000

Data Index: 348451 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.8268. Min Act: -0.0000

Data Index: 432250 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.7133. Min Act: -0.0000

Data Index: 44605 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.6437. Min Act: -0.0001

Data Index: 1092908 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.6845. Min Act: -0.0000

Data Index: 822325 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.6308. Min Act: -0.0000

Data Index: 58719 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.6407. Min Act: -0.0001

Data Index: 491386 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.6129. Min Act: -0.0001

Data Index: 658757 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.6325. Min Act: -0.0000

Data Index: 819912 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.5871. Min Act: -0.0000

Data Index: 981452 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.5847. Min Act: -0.0000

Data Index: 451889 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.5636. Min Act: -0.0001

Data Index: 170250 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.5828. Min Act: -0.0000

Data Index: 338546 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.5384. Min Act: -0.0000

Data Index: 182434 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.5187. Min Act: -0.0000

Data Index: 140101 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.5397. Min Act: -0.0001

Data Index: 662079 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.5537. Min Act: -0.0000

Data Index: 1094951 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.5528. Min Act: -0.0001

Data Index: 1013031 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.5662. Min Act: -0.0000

Data Index: 392977 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1265635 (C4 (Web Text))

Max Activating Token Index: 356