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

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

Neuron 1948 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1990. Min Act: -0.0001

Data Index: 1384001 (Python Code)

Max Activating Token Index: 999

Text #1

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1770. Min Act: -0.0001

Data Index: 1493735 (Python Code)

Max Activating Token Index: 298

Text #2

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1781. Min Act: -0.0001

Data Index: 1441477 (Python Code)

Max Activating Token Index: 798

Text #3

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1967. Min Act: -0.0001

Data Index: 1432338 (Python Code)

Max Activating Token Index: 110

Text #4

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1602. Min Act: -0.0001

Data Index: 1538122 (Python Code)

Max Activating Token Index: 616

Text #5

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1545. Min Act: -0.0001

Data Index: 1523070 (Python Code)

Max Activating Token Index: 727

Text #6

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1571. Min Act: -0.0001

Data Index: 1623887 (Python Code)

Max Activating Token Index: 531

Text #7

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1364. Min Act: -0.0001

Data Index: 1548439 (Python Code)

Max Activating Token Index: 875

Text #8

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1685. Min Act: -0.0001

Data Index: 1400700 (Python Code)

Max Activating Token Index: 212

Text #9

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1439. Min Act: -0.0001

Data Index: 1629492 (Python Code)

Max Activating Token Index: 284

Text #10

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1486. Min Act: -0.0001

Data Index: 1406986 (Python Code)

Max Activating Token Index: 498

Text #11

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1508. Min Act: -0.0002

Data Index: 1448508 (Python Code)

Max Activating Token Index: 37

Text #12

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1280. Min Act: -0.0001

Data Index: 1604206 (Python Code)

Max Activating Token Index: 436

Text #13

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1335. Min Act: -0.0001

Data Index: 1492272 (Python Code)

Max Activating Token Index: 534

Text #14

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1149. Min Act: -0.0001

Data Index: 1387354 (Python Code)

Max Activating Token Index: 252

Text #15

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1310. Min Act: -0.0001

Data Index: 1522969 (Python Code)

Max Activating Token Index: 553

Text #16

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1256. Min Act: -0.0001

Data Index: 1550779 (Python Code)

Max Activating Token Index: 58

Text #17

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1241. Min Act: -0.0001

Data Index: 1654106 (Python Code)

Max Activating Token Index: 639

Text #18

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1226. Min Act: -0.0001

Data Index: 1580216 (Python Code)

Max Activating Token Index: 464

Text #19

Max Range: 0.1990. Min Range: -0.1990

Max Act: 0.1009. Min Act: -0.0001

Data Index: 1495222 (Python Code)

Max Activating Token Index: 812