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

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

Neuron 339 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: 1.7397. Min Range: -1.7397

Max Act: 1.7397. Min Act: 0.0001

Data Index: 1487509 (Python Code)

Max Activating Token Index: 103

Text #1

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.5052. Min Act: 0.0000

Data Index: 1626614 (Python Code)

Max Activating Token Index: 261

Text #2

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.4140. Min Act: -0.0000

Data Index: 1614990 (Python Code)

Max Activating Token Index: 980

Text #3

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.2864. Min Act: 0.0000

Data Index: 1030430 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.2563. Min Act: -0.0000

Data Index: 560970 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.2435. Min Act: 0.0000

Data Index: 1403019 (Python Code)

Max Activating Token Index: 403

Text #6

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.2317. Min Act: -0.0000

Data Index: 1635903 (Python Code)

Max Activating Token Index: 350

Text #7

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.0612. Min Act: 0.0000

Data Index: 1517268 (Python Code)

Max Activating Token Index: 372

Text #8

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.1117. Min Act: -0.0000

Data Index: 1395501 (Python Code)

Max Activating Token Index: 557

Text #9

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.1299. Min Act: -0.0000

Data Index: 1268376 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.0325. Min Act: -0.0000

Data Index: 1367165 (Python Code)

Max Activating Token Index: 1017

Text #11

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.1737. Min Act: -0.0000

Data Index: 1573508 (Python Code)

Max Activating Token Index: 554

Text #12

Max Range: 1.7397. Min Range: -1.7397

Max Act: 0.9867. Min Act: -0.0000

Data Index: 1619396 (Python Code)

Max Activating Token Index: 830

Text #13

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.0564. Min Act: -0.0000

Data Index: 1490531 (Python Code)

Max Activating Token Index: 384

Text #14

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.0239. Min Act: 0.0000

Data Index: 1647618 (Python Code)

Max Activating Token Index: 562

Text #15

Max Range: 1.7397. Min Range: -1.7397

Max Act: 0.9995. Min Act: 0.0000

Data Index: 1609943 (Python Code)

Max Activating Token Index: 524

Text #16

Max Range: 1.7397. Min Range: -1.7397

Max Act: 0.9972. Min Act: 0.0000

Data Index: 294846 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 1.7397. Min Range: -1.7397

Max Act: 0.9797. Min Act: 0.0000

Data Index: 1312865 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 1.7397. Min Range: -1.7397

Max Act: 0.9813. Min Act: -0.0000

Data Index: 736076 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 1.7397. Min Range: -1.7397

Max Act: 1.0211. Min Act: 0.0000

Data Index: 438180 (C4 (Web Text))

Max Activating Token Index: 886