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

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

Neuron 2733 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1573. Min Act: -0.0000

Data Index: 1164785 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1615. Min Act: -0.0000

Data Index: 351182 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1550. Min Act: -0.0000

Data Index: 1604779 (Python Code)

Max Activating Token Index: 711

Text #3

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1545. Min Act: -0.0000

Data Index: 1121698 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1479. Min Act: -0.0000

Data Index: 551178 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1467. Min Act: -0.0000

Data Index: 1404365 (Python Code)

Max Activating Token Index: 604

Text #6

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1466. Min Act: -0.0000

Data Index: 1108732 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1438. Min Act: -0.0000

Data Index: 1591974 (Python Code)

Max Activating Token Index: 203

Text #8

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1133063 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1445. Min Act: -0.0000

Data Index: 180588 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1465. Min Act: -0.0000

Data Index: 1250130 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1448. Min Act: -0.0000

Data Index: 1261237 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1388. Min Act: -0.0000

Data Index: 1135013 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1301. Min Act: -0.0000

Data Index: 555142 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1336. Min Act: -0.0000

Data Index: 211115 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1284. Min Act: -0.0000

Data Index: 350889 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1367. Min Act: -0.0000

Data Index: 718098 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1314. Min Act: -0.0000

Data Index: 1328288 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1315. Min Act: -0.0000

Data Index: 165485 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1319. Min Act: -0.0000

Data Index: 368302 (C4 (Web Text))

Max Activating Token Index: 575