Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2090 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0424. Min Act: -0.0004

Data Index: 544277 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0412. Min Act: -0.0004

Data Index: 882079 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0399. Min Act: -0.0004

Data Index: 609122 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0391. Min Act: -0.0004

Data Index: 1190260 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0393. Min Act: -0.0004

Data Index: 1292736 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0385. Min Act: -0.0004

Data Index: 974234 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0340. Min Act: -0.0004

Data Index: 706285 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0382. Min Act: -0.0004

Data Index: 964803 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0362. Min Act: -0.0004

Data Index: 1165348 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0333. Min Act: -0.0004

Data Index: 915137 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0370. Min Act: -0.0004

Data Index: 532765 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0335. Min Act: -0.0004

Data Index: 351684 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0344. Min Act: -0.0004

Data Index: 1181255 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0379. Min Act: -0.0004

Data Index: 1251646 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0338. Min Act: -0.0004

Data Index: 1296474 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0345. Min Act: -0.0004

Data Index: 951099 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0336. Min Act: -0.0004

Data Index: 127687 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0341. Min Act: -0.0004

Data Index: 1193070 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0322. Min Act: -0.0004

Data Index: 1321847 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0325. Min Act: -0.0004

Data Index: 817127 (C4 (Web Text))

Max Activating Token Index: 413