Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1620 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0433. Min Act: -0.0006

Data Index: 773698 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0380. Min Act: -0.0006

Data Index: 30107 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0376. Min Act: -0.0006

Data Index: 1310648 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0357. Min Act: -0.0006

Data Index: 657686 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0364. Min Act: -0.0006

Data Index: 1255192 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0368. Min Act: -0.0006

Data Index: 1296213 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0369. Min Act: -0.0006

Data Index: 270678 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0368. Min Act: -0.0006

Data Index: 1090213 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0359. Min Act: -0.0006

Data Index: 1029882 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0352. Min Act: -0.0006

Data Index: 606716 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0344. Min Act: -0.0006

Data Index: 274428 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0358. Min Act: -0.0006

Data Index: 581579 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0347. Min Act: -0.0006

Data Index: 267664 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0339. Min Act: -0.0006

Data Index: 213975 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0344. Min Act: -0.0006

Data Index: 916273 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0355. Min Act: -0.0006

Data Index: 468929 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0354. Min Act: -0.0006

Data Index: 1332139 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0346. Min Act: -0.0006

Data Index: 481096 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0353. Min Act: -0.0006

Data Index: 695515 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0352. Min Act: -0.0006

Data Index: 1266006 (C4 (Web Text))

Max Activating Token Index: 140