Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2027 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0379. Min Act: -0.0003

Data Index: 1005969 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0378. Min Act: -0.0003

Data Index: 283630 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0353. Min Act: -0.0003

Data Index: 434863 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0345. Min Act: -0.0003

Data Index: 1075540 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0307. Min Act: -0.0003

Data Index: 268386 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0306. Min Act: -0.0003

Data Index: 1071819 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1356176 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0277. Min Act: -0.0003

Data Index: 444686 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0268. Min Act: -0.0003

Data Index: 1121388 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0256. Min Act: -0.0004

Data Index: 510956 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0225. Min Act: -0.0003

Data Index: 1329141 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1090775 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0277. Min Act: -0.0003

Data Index: 30309 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0257. Min Act: -0.0004

Data Index: 1294613 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0260. Min Act: -0.0003

Data Index: 600249 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0262. Min Act: -0.0003

Data Index: 1286141 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0258. Min Act: -0.0003

Data Index: 827505 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0244. Min Act: -0.0003

Data Index: 727239 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0255. Min Act: -0.0003

Data Index: 1078211 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0249. Min Act: -0.0003

Data Index: 1311545 (C4 (Web Text))

Max Activating Token Index: 260