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

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

Neuron 3448 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.4801. Min Act: -0.0000

Data Index: 1375485 (Python Code)

Max Activating Token Index: 946

Text #1

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.6151. Min Act: -0.0000

Data Index: 1615427 (Python Code)

Max Activating Token Index: 373

Text #2

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.3964. Min Act: -0.0000

Data Index: 1395324 (Python Code)

Max Activating Token Index: 1011

Text #3

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.4408. Min Act: -0.0000

Data Index: 1589994 (Python Code)

Max Activating Token Index: 25

Text #4

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.2589. Min Act: -0.0000

Data Index: 1486216 (Python Code)

Max Activating Token Index: 16

Text #5

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.3071. Min Act: -0.0000

Data Index: 1651343 (Python Code)

Max Activating Token Index: 331

Text #6

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.2766. Min Act: -0.0000

Data Index: 1368416 (Python Code)

Max Activating Token Index: 11

Text #7

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.2769. Min Act: -0.0000

Data Index: 1493532 (Python Code)

Max Activating Token Index: 11

Text #8

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.1243. Min Act: -0.0000

Data Index: 1410672 (Python Code)

Max Activating Token Index: 44

Text #9

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.1991. Min Act: -0.0000

Data Index: 1597102 (Python Code)

Max Activating Token Index: 147

Text #10

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1466884 (Python Code)

Max Activating Token Index: 361

Text #11

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.0200. Min Act: -0.0000

Data Index: 1425854 (Python Code)

Max Activating Token Index: 895

Text #12

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.1633. Min Act: -0.0000

Data Index: 1378967 (Python Code)

Max Activating Token Index: 795

Text #13

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.1183. Min Act: -0.0000

Data Index: 1620916 (Python Code)

Max Activating Token Index: 12

Text #14

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.0831. Min Act: -0.0000

Data Index: 1364390 (Python Code)

Max Activating Token Index: 12

Text #15

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.1031. Min Act: -0.0000

Data Index: 1570577 (Python Code)

Max Activating Token Index: 403

Text #16

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.0771. Min Act: -0.0000

Data Index: 1492681 (Python Code)

Max Activating Token Index: 416

Text #17

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.0971. Min Act: -0.0000

Data Index: 1625239 (Python Code)

Max Activating Token Index: 15

Text #18

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.1307. Min Act: -0.0000

Data Index: 1517399 (Python Code)

Max Activating Token Index: 208

Text #19

Max Range: 1.6151. Min Range: -1.6151

Max Act: 1.0477. Min Act: -0.0000

Data Index: 1433980 (Python Code)

Max Activating Token Index: 579