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

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

Neuron 4370 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: 0.1888. Min Range: -0.1888

Max Act: 0.1888. Min Act: -0.0001

Data Index: 1413197 (Python Code)

Max Activating Token Index: 810

Text #1

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1398. Min Act: -0.0001

Data Index: 211840 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1369. Min Act: -0.0001

Data Index: 758571 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1479. Min Act: -0.0001

Data Index: 1390542 (Python Code)

Max Activating Token Index: 551

Text #4

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1526694 (Python Code)

Max Activating Token Index: 376

Text #5

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1306. Min Act: -0.0001

Data Index: 1412637 (Python Code)

Max Activating Token Index: 568

Text #6

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1279. Min Act: -0.0001

Data Index: 1123343 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1384. Min Act: -0.0001

Data Index: 1636154 (Python Code)

Max Activating Token Index: 536

Text #8

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1127. Min Act: -0.0001

Data Index: 1448928 (Python Code)

Max Activating Token Index: 907

Text #9

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1169. Min Act: -0.0001

Data Index: 987456 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1288. Min Act: -0.0001

Data Index: 1393624 (Python Code)

Max Activating Token Index: 622

Text #11

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1234. Min Act: -0.0001

Data Index: 1373943 (Python Code)

Max Activating Token Index: 221

Text #12

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1162. Min Act: -0.0001

Data Index: 1583649 (Python Code)

Max Activating Token Index: 584

Text #13

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1186. Min Act: -0.0001

Data Index: 1406769 (Python Code)

Max Activating Token Index: 530

Text #14

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1527183 (Python Code)

Max Activating Token Index: 447

Text #15

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1522709 (Python Code)

Max Activating Token Index: 671

Text #16

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1167. Min Act: -0.0001

Data Index: 1643130 (Python Code)

Max Activating Token Index: 107

Text #17

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1065. Min Act: -0.0001

Data Index: 1461513 (Python Code)

Max Activating Token Index: 304

Text #18

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1513544 (Python Code)

Max Activating Token Index: 683

Text #19

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1094. Min Act: -0.0001

Data Index: 1622282 (Python Code)

Max Activating Token Index: 329