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

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

Neuron 2874 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1512367 (Python Code)

Max Activating Token Index: 558

Text #1

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0421. Min Act: -0.0002

Data Index: 383364 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1595165 (Python Code)

Max Activating Token Index: 635

Text #3

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1464468 (Python Code)

Max Activating Token Index: 46

Text #4

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1272997 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0387. Min Act: -0.0002

Data Index: 832515 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0399. Min Act: -0.0002

Data Index: 1323541 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0395. Min Act: -0.0002

Data Index: 327792 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0398. Min Act: -0.0002

Data Index: 557478 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1403352 (Python Code)

Max Activating Token Index: 137

Text #10

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1138170 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0380. Min Act: -0.0002

Data Index: 841918 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1042277 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0364. Min Act: -0.0002

Data Index: 236745 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0374. Min Act: -0.0002

Data Index: 1488215 (Python Code)

Max Activating Token Index: 492

Text #15

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0358. Min Act: -0.0002

Data Index: 1318257 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0372. Min Act: -0.0002

Data Index: 297250 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1281446 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0374. Min Act: -0.0002

Data Index: 1074413 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0353. Min Act: -0.0002

Data Index: 1559818 (Python Code)

Max Activating Token Index: 687