Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2014 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1775. Min Act: -0.0000

Data Index: 766008 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1630. Min Act: -0.0000

Data Index: 207591 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1653. Min Act: -0.0000

Data Index: 524700 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1561. Min Act: -0.0000

Data Index: 1182567 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1532. Min Act: -0.0000

Data Index: 293546 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1472. Min Act: -0.0000

Data Index: 342025 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1406. Min Act: -0.0000

Data Index: 1177518 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1481. Min Act: -0.0000

Data Index: 76355 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1399. Min Act: -0.0000

Data Index: 105817 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1390. Min Act: -0.0000

Data Index: 284371 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1378. Min Act: -0.0000

Data Index: 390169 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1312. Min Act: -0.0000

Data Index: 1437076 (Python Code)

Max Activating Token Index: 358

Text #12

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1341. Min Act: -0.0000

Data Index: 922638 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1369. Min Act: -0.0000

Data Index: 459142 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1315. Min Act: -0.0000

Data Index: 1489314 (Python Code)

Max Activating Token Index: 151

Text #15

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1313. Min Act: -0.0000

Data Index: 669268 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1428480 (Python Code)

Max Activating Token Index: 138

Text #17

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1238. Min Act: -0.0000

Data Index: 1376375 (Python Code)

Max Activating Token Index: 218

Text #18

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1267. Min Act: -0.0000

Data Index: 209055 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1424437 (Python Code)

Max Activating Token Index: 677