Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4748 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1634. Min Act: -0.0000

Data Index: 1128122 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1491. Min Act: -0.0000

Data Index: 1607153 (Python Code)

Max Activating Token Index: 410

Text #2

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1525. Min Act: -0.0000

Data Index: 131417 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1406. Min Act: -0.0000

Data Index: 346918 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1357. Min Act: -0.0000

Data Index: 614401 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1370. Min Act: 0.0000

Data Index: 461413 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1369. Min Act: -0.0000

Data Index: 145853 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1401. Min Act: -0.0000

Data Index: 1638954 (Python Code)

Max Activating Token Index: 435

Text #8

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1393. Min Act: -0.0000

Data Index: 380406 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1370. Min Act: -0.0000

Data Index: 593329 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1309. Min Act: -0.0000

Data Index: 1174811 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1330. Min Act: -0.0000

Data Index: 1130290 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1351. Min Act: -0.0000

Data Index: 211306 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1283. Min Act: -0.0000

Data Index: 1564014 (Python Code)

Max Activating Token Index: 403

Text #14

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1342. Min Act: -0.0000

Data Index: 1424611 (Python Code)

Max Activating Token Index: 892

Text #15

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1381. Min Act: -0.0000

Data Index: 1043345 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1294. Min Act: 0.0000

Data Index: 152045 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1336. Min Act: -0.0000

Data Index: 73359 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1380. Min Act: -0.0000

Data Index: 903832 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1319. Min Act: -0.0000

Data Index: 1186503 (C4 (Web Text))

Max Activating Token Index: 466