Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1814 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1562. Min Act: -0.0005

Data Index: 389233 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1496. Min Act: -0.0005

Data Index: 382820 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1366. Min Act: -0.0005

Data Index: 1069690 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1346. Min Act: -0.0005

Data Index: 571427 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1334. Min Act: -0.0004

Data Index: 277082 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1279. Min Act: -0.0005

Data Index: 324829 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1319. Min Act: -0.0005

Data Index: 1246751 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1257. Min Act: -0.0005

Data Index: 675215 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1300. Min Act: -0.0005

Data Index: 491831 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1247. Min Act: -0.0005

Data Index: 63188 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1290. Min Act: -0.0005

Data Index: 696304 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1238. Min Act: -0.0005

Data Index: 296944 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1270. Min Act: -0.0005

Data Index: 1078743 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1308. Min Act: -0.0005

Data Index: 1116765 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1287. Min Act: -0.0005

Data Index: 1347639 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1234. Min Act: -0.0005

Data Index: 960665 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1217. Min Act: -0.0005

Data Index: 844139 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1267. Min Act: -0.0005

Data Index: 1001601 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1220. Min Act: -0.0005

Data Index: 799592 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1248. Min Act: -0.0005

Data Index: 920513 (C4 (Web Text))

Max Activating Token Index: 636