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

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

Neuron 2028 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: 0.0458. Min Range: -0.0458

Max Act: 0.0458. Min Act: -0.0000

Data Index: 1016611 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0393. Min Act: -0.0000

Data Index: 1104323 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0365. Min Act: -0.0000

Data Index: 1607665 (Python Code)

Max Activating Token Index: 40

Text #3

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0357. Min Act: -0.0000

Data Index: 811164 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0357. Min Act: -0.0000

Data Index: 1286607 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0362. Min Act: -0.0000

Data Index: 360267 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0353. Min Act: -0.0000

Data Index: 1628813 (Python Code)

Max Activating Token Index: 862

Text #7

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0338. Min Act: -0.0000

Data Index: 1368796 (Python Code)

Max Activating Token Index: 659

Text #8

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0352. Min Act: -0.0001

Data Index: 756056 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0320. Min Act: -0.0000

Data Index: 1128551 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0325. Min Act: -0.0001

Data Index: 1527374 (Python Code)

Max Activating Token Index: 398

Text #11

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0314. Min Act: -0.0000

Data Index: 1200149 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0298. Min Act: -0.0000

Data Index: 1427239 (Python Code)

Max Activating Token Index: 41

Text #13

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0303. Min Act: -0.0001

Data Index: 138829 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0315. Min Act: -0.0001

Data Index: 1605042 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0316. Min Act: -0.0000

Data Index: 665149 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0313. Min Act: -0.0000

Data Index: 1624268 (Python Code)

Max Activating Token Index: 658

Text #17

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0301. Min Act: -0.0000

Data Index: 1627313 (Python Code)

Max Activating Token Index: 563

Text #18

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0297. Min Act: -0.0001

Data Index: 448659 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0308. Min Act: -0.0001

Data Index: 720582 (C4 (Web Text))

Max Activating Token Index: 387