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

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

Neuron 394 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1848. Min Act: 0.0001

Data Index: 220946 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1565. Min Act: 0.0002

Data Index: 1529145 (Python Code)

Max Activating Token Index: 404

Text #2

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1446. Min Act: 0.0003

Data Index: 830601 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1495. Min Act: 0.0001

Data Index: 1605743 (Python Code)

Max Activating Token Index: 1001

Text #4

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1566. Min Act: -0.0000

Data Index: 1624766 (Python Code)

Max Activating Token Index: 986

Text #5

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1418. Min Act: -0.0000

Data Index: 378371 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1498. Min Act: 0.0001

Data Index: 1456824 (Python Code)

Max Activating Token Index: 150

Text #7

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1413. Min Act: 0.0001

Data Index: 621457 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1403. Min Act: 0.0001

Data Index: 1572423 (Python Code)

Max Activating Token Index: 991

Text #9

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1401. Min Act: 0.0001

Data Index: 943641 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1393. Min Act: -0.0000

Data Index: 71159 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1339. Min Act: 0.0002

Data Index: 1385236 (Python Code)

Max Activating Token Index: 158

Text #12

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1283. Min Act: 0.0002

Data Index: 1607349 (Python Code)

Max Activating Token Index: 593

Text #13

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1282. Min Act: 0.0003

Data Index: 1445502 (Python Code)

Max Activating Token Index: 563

Text #14

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1267. Min Act: 0.0001

Data Index: 1390417 (Python Code)

Max Activating Token Index: 624

Text #15

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1312. Min Act: 0.0001

Data Index: 1643899 (Python Code)

Max Activating Token Index: 307

Text #16

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1349. Min Act: 0.0003

Data Index: 634504 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1214. Min Act: 0.0003

Data Index: 1423970 (Python Code)

Max Activating Token Index: 682

Text #18

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1268. Min Act: 0.0002

Data Index: 845880 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 0.1848. Min Range: -0.1848

Max Act: 0.1268. Min Act: 0.0002

Data Index: 1603215 (Python Code)

Max Activating Token Index: 94