Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3491 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0433. Min Act: -0.0001

Data Index: 48325 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1175512 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0338. Min Act: -0.0001

Data Index: 994719 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0278. Min Act: -0.0001

Data Index: 1108098 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0315. Min Act: -0.0001

Data Index: 450278 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0257. Min Act: -0.0001

Data Index: 248792 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0290. Min Act: -0.0001

Data Index: 870630 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0298. Min Act: -0.0001

Data Index: 1138413 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0275. Min Act: -0.0001

Data Index: 1222411 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0288. Min Act: -0.0001

Data Index: 334063 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0275. Min Act: -0.0001

Data Index: 338920 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0268. Min Act: -0.0001

Data Index: 549048 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0260. Min Act: -0.0001

Data Index: 1183561 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0272. Min Act: -0.0001

Data Index: 494339 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0287. Min Act: -0.0001

Data Index: 379461 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0230. Min Act: -0.0001

Data Index: 1065473 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0219. Min Act: -0.0002

Data Index: 544896 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0235. Min Act: -0.0001

Data Index: 841739 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0237. Min Act: -0.0001

Data Index: 359773 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0262. Min Act: -0.0001

Data Index: 783625 (C4 (Web Text))

Max Activating Token Index: 885