Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1324 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1615. Min Act: -0.0001

Data Index: 291093 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1530. Min Act: -0.0001

Data Index: 806646 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1611. Min Act: 0.0000

Data Index: 294178 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1491. Min Act: -0.0000

Data Index: 189195 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1530. Min Act: -0.0001

Data Index: 203644 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1628. Min Act: -0.0001

Data Index: 1330873 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1445. Min Act: -0.0001

Data Index: 804482 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1509. Min Act: -0.0001

Data Index: 181967 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1457. Min Act: -0.0000

Data Index: 741804 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1396. Min Act: -0.0001

Data Index: 141873 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1343. Min Act: -0.0001

Data Index: 224262 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1380. Min Act: -0.0001

Data Index: 555947 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1282. Min Act: -0.0001

Data Index: 893316 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1423. Min Act: -0.0001

Data Index: 684058 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1365. Min Act: -0.0001

Data Index: 1165618 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1348. Min Act: -0.0001

Data Index: 444857 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1340. Min Act: -0.0001

Data Index: 1137230 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1335. Min Act: -0.0001

Data Index: 749285 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1306. Min Act: -0.0001

Data Index: 262225 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1291. Min Act: -0.0001

Data Index: 1271369 (C4 (Web Text))

Max Activating Token Index: 967