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

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

Neuron 251 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0689. Min Act: -0.0000

Data Index: 377433 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0470. Min Act: -0.0000

Data Index: 766221 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0470. Min Act: -0.0000

Data Index: 180285 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0469. Min Act: -0.0000

Data Index: 707650 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0462. Min Act: -0.0001

Data Index: 719857 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0426. Min Act: -0.0000

Data Index: 1269404 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0433. Min Act: -0.0000

Data Index: 180350 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0372. Min Act: -0.0000

Data Index: 1268036 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0402. Min Act: -0.0001

Data Index: 1260291 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0366. Min Act: -0.0000

Data Index: 1000163 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0376. Min Act: -0.0000

Data Index: 82020 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0366. Min Act: -0.0000

Data Index: 874740 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0374. Min Act: -0.0000

Data Index: 1055411 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0393. Min Act: -0.0000

Data Index: 1005016 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0394. Min Act: -0.0000

Data Index: 1178756 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0357. Min Act: -0.0000

Data Index: 236081 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0375. Min Act: -0.0000

Data Index: 660357 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0382. Min Act: -0.0000

Data Index: 483144 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0372. Min Act: -0.0001

Data Index: 13017 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0373. Min Act: -0.0000

Data Index: 1297969 (C4 (Web Text))

Max Activating Token Index: 385