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

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

Neuron 5625 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1618. Min Act: -0.0003

Data Index: 1147086 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1519. Min Act: -0.0002

Data Index: 1035332 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1494. Min Act: -0.0002

Data Index: 310388 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1466. Min Act: -0.0002

Data Index: 458735 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1504. Min Act: -0.0002

Data Index: 1135252 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1466. Min Act: -0.0002

Data Index: 1387452 (Python Code)

Max Activating Token Index: 304

Text #6

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1436. Min Act: -0.0002

Data Index: 1401950 (Python Code)

Max Activating Token Index: 696

Text #7

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1436. Min Act: -0.0002

Data Index: 1420832 (Python Code)

Max Activating Token Index: 2

Text #8

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1482. Min Act: -0.0002

Data Index: 1538243 (Python Code)

Max Activating Token Index: 867

Text #9

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1409. Min Act: -0.0002

Data Index: 292511 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1417. Min Act: -0.0002

Data Index: 1461276 (Python Code)

Max Activating Token Index: 842

Text #11

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1403. Min Act: -0.0002

Data Index: 365671 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1394. Min Act: -0.0002

Data Index: 410585 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1376. Min Act: -0.0002

Data Index: 1186395 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1370. Min Act: -0.0002

Data Index: 1234773 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1373. Min Act: -0.0002

Data Index: 1233170 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1383. Min Act: -0.0002

Data Index: 1168857 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1365. Min Act: -0.0002

Data Index: 1579499 (Python Code)

Max Activating Token Index: 271

Text #18

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1349. Min Act: -0.0002

Data Index: 973721 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1346. Min Act: -0.0002

Data Index: 477739 (C4 (Web Text))

Max Activating Token Index: 778