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

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

Neuron 3223 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0455. Min Act: -0.0002

Data Index: 636312 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0428. Min Act: -0.0002

Data Index: 743931 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0404. Min Act: -0.0002

Data Index: 249688 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0394. Min Act: -0.0001

Data Index: 1106397 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0396. Min Act: -0.0002

Data Index: 147004 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0373. Min Act: -0.0002

Data Index: 1260217 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0370. Min Act: -0.0001

Data Index: 160982 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0381. Min Act: -0.0002

Data Index: 618238 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0345. Min Act: -0.0001

Data Index: 116809 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0316. Min Act: -0.0002

Data Index: 910889 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0328. Min Act: -0.0001

Data Index: 1205402 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0361. Min Act: -0.0002

Data Index: 153719 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0349. Min Act: -0.0002

Data Index: 398371 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0347. Min Act: -0.0002

Data Index: 202461 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0343. Min Act: -0.0002

Data Index: 899140 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1301772 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0346. Min Act: -0.0001

Data Index: 126356 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1288663 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0342. Min Act: -0.0002

Data Index: 80734 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0321. Min Act: -0.0002

Data Index: 649939 (C4 (Web Text))

Max Activating Token Index: 614