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

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

Neuron 4687 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2781. Min Act: -0.0000

Data Index: 137696 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2632. Min Act: -0.0000

Data Index: 365540 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2396. Min Act: 0.0000

Data Index: 241035 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2445. Min Act: -0.0000

Data Index: 923918 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2442. Min Act: -0.0000

Data Index: 391902 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2447. Min Act: -0.0000

Data Index: 327344 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2370. Min Act: -0.0000

Data Index: 749699 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2372. Min Act: -0.0000

Data Index: 481515 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2334. Min Act: -0.0000

Data Index: 755309 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2349. Min Act: -0.0000

Data Index: 1143205 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2352. Min Act: -0.0000

Data Index: 595839 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2352. Min Act: -0.0000

Data Index: 565328 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2344. Min Act: -0.0000

Data Index: 1204882 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2305. Min Act: -0.0000

Data Index: 1290679 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2370. Min Act: -0.0000

Data Index: 901840 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2284. Min Act: 0.0001

Data Index: 331560 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2275. Min Act: -0.0000

Data Index: 715474 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2283. Min Act: -0.0000

Data Index: 1122400 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2174. Min Act: 0.0000

Data Index: 1130226 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2183. Min Act: -0.0000

Data Index: 755336 (C4 (Web Text))

Max Activating Token Index: 992