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

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

Neuron 2948 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1599. Min Act: -0.0001

Data Index: 1014903 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1678. Min Act: -0.0001

Data Index: 359345 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1504. Min Act: -0.0001

Data Index: 924093 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1592. Min Act: -0.0001

Data Index: 425096 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1629. Min Act: -0.0001

Data Index: 704467 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1507. Min Act: -0.0001

Data Index: 505930 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1482. Min Act: -0.0001

Data Index: 429413 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1620. Min Act: -0.0001

Data Index: 1043485 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1442. Min Act: -0.0001

Data Index: 1135855 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1547. Min Act: -0.0001

Data Index: 299096 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1403. Min Act: -0.0001

Data Index: 704879 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1390. Min Act: -0.0001

Data Index: 368014 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1446. Min Act: -0.0001

Data Index: 623403 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1461. Min Act: -0.0001

Data Index: 1018510 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1413. Min Act: -0.0001

Data Index: 252656 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1438. Min Act: -0.0001

Data Index: 1116749 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1448. Min Act: -0.0001

Data Index: 402590 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1418. Min Act: -0.0001

Data Index: 702820 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1508. Min Act: -0.0001

Data Index: 105886 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1447. Min Act: -0.0001

Data Index: 465035 (C4 (Web Text))

Max Activating Token Index: 9