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

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

Neuron 5560 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: 0.2575. Min Range: -0.2575

Max Act: 0.2385. Min Act: -0.0000

Data Index: 1640046 (Python Code)

Max Activating Token Index: 419

Text #1

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.2575. Min Act: -0.0000

Data Index: 1456841 (Python Code)

Max Activating Token Index: 1015

Text #2

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1893. Min Act: -0.0000

Data Index: 1508360 (Python Code)

Max Activating Token Index: 174

Text #3

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1724. Min Act: -0.0000

Data Index: 1589454 (Python Code)

Max Activating Token Index: 244

Text #4

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1693. Min Act: -0.0000

Data Index: 1384344 (Python Code)

Max Activating Token Index: 483

Text #5

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1561. Min Act: -0.0000

Data Index: 1404655 (Python Code)

Max Activating Token Index: 568

Text #6

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1411. Min Act: -0.0000

Data Index: 1550849 (Python Code)

Max Activating Token Index: 437

Text #7

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1403. Min Act: -0.0000

Data Index: 1402359 (Python Code)

Max Activating Token Index: 361

Text #8

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1359903 (Python Code)

Max Activating Token Index: 147

Text #9

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1366. Min Act: -0.0000

Data Index: 1585355 (Python Code)

Max Activating Token Index: 458

Text #10

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1355. Min Act: -0.0000

Data Index: 1471255 (Python Code)

Max Activating Token Index: 336

Text #11

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1194. Min Act: -0.0000

Data Index: 1491616 (Python Code)

Max Activating Token Index: 428

Text #12

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1206. Min Act: -0.0000

Data Index: 1586011 (Python Code)

Max Activating Token Index: 969

Text #13

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1225. Min Act: -0.0000

Data Index: 1614090 (Python Code)

Max Activating Token Index: 126

Text #14

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1204. Min Act: -0.0000

Data Index: 153949 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1545773 (Python Code)

Max Activating Token Index: 693

Text #16

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1223. Min Act: -0.0000

Data Index: 1361142 (Python Code)

Max Activating Token Index: 865

Text #17

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1380571 (Python Code)

Max Activating Token Index: 252

Text #18

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1100. Min Act: -0.0000

Data Index: 1549573 (Python Code)

Max Activating Token Index: 409

Text #19

Max Range: 0.2575. Min Range: -0.2575

Max Act: 0.1039. Min Act: -0.0000

Data Index: 1646740 (Python Code)

Max Activating Token Index: 796