Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3098 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0587. Min Act: -0.0000

Data Index: 308676 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0392. Min Act: -0.0001

Data Index: 1528403 (Python Code)

Max Activating Token Index: 982

Text #2

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0404. Min Act: -0.0001

Data Index: 1357536 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0433. Min Act: -0.0001

Data Index: 1003692 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0361. Min Act: -0.0001

Data Index: 665346 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0387. Min Act: -0.0001

Data Index: 259191 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0397. Min Act: -0.0000

Data Index: 1097740 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0372. Min Act: -0.0001

Data Index: 1475573 (Python Code)

Max Activating Token Index: 812

Text #8

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0351. Min Act: -0.0001

Data Index: 421006 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0345. Min Act: -0.0001

Data Index: 562301 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0414. Min Act: -0.0001

Data Index: 1321747 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0345. Min Act: -0.0001

Data Index: 54974 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0377. Min Act: -0.0001

Data Index: 1245705 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0368. Min Act: -0.0001

Data Index: 606795 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0382. Min Act: -0.0001

Data Index: 473140 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0337. Min Act: -0.0001

Data Index: 542578 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0338. Min Act: -0.0001

Data Index: 1241932 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0361. Min Act: -0.0001

Data Index: 1619793 (Python Code)

Max Activating Token Index: 532

Text #18

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0339. Min Act: -0.0001

Data Index: 1362419 (Python Code)

Max Activating Token Index: 62

Text #19

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0362. Min Act: -0.0001

Data Index: 191012 (C4 (Web Text))

Max Activating Token Index: 467