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

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

Neuron 4930 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1766. Min Range: -0.1766

Max Act: 0.1606. Min Act: -0.0000

Data Index: 174420 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.1766. Min Range: -0.1766

Max Act: 0.1766. Min Act: -0.0000

Data Index: 763931 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.1766. Min Range: -0.1766

Max Act: 0.1346. Min Act: -0.0000

Data Index: 729536 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.1766. Min Range: -0.1766

Max Act: 0.1465. Min Act: -0.0000

Data Index: 439847 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 0.1766. Min Range: -0.1766

Max Act: 0.1505. Min Act: -0.0000

Data Index: 852450 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 0.1766. Min Range: -0.1766

Max Act: 0.1355. Min Act: -0.0000

Data Index: 292207 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.1766. Min Range: -0.1766

Max Act: 0.1458. Min Act: -0.0000

Data Index: 578965 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 0.1766. Min Range: -0.1766

Max Act: 0.1465. Min Act: -0.0000

Data Index: 1020246 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 0.1766. Min Range: -0.1766

Max Act: 0.1273. Min Act: -0.0000

Data Index: 752077 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.1766. Min Range: -0.1766

Max Act: 0.1239. Min Act: -0.0000

Data Index: 667874 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.1766. Min Range: -0.1766

Max Act: 0.1213. Min Act: -0.0000

Data Index: 1332345 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 0.1766. Min Range: -0.1766

Max Act: 0.1264. Min Act: -0.0000

Data Index: 21631 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 0.1766. Min Range: -0.1766

Max Act: 0.1346. Min Act: -0.0000

Data Index: 401339 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.1766. Min Range: -0.1766

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1290811 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 0.1766. Min Range: -0.1766

Max Act: 0.1379. Min Act: -0.0000

Data Index: 1257595 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.1766. Min Range: -0.1766

Max Act: 0.1242. Min Act: -0.0000

Data Index: 621994 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.1766. Min Range: -0.1766

Max Act: 0.1223. Min Act: -0.0000

Data Index: 141816 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.1766. Min Range: -0.1766

Max Act: 0.1219. Min Act: -0.0000

Data Index: 645344 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.1766. Min Range: -0.1766

Max Act: 0.1170. Min Act: -0.0000

Data Index: 623913 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.1766. Min Range: -0.1766

Max Act: 0.1247. Min Act: -0.0000

Data Index: 1134839 (C4 (Web Text))

Max Activating Token Index: 306