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

Dataset: The Pile

Neuron 641 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.2082. Min Act: -0.0000

Data Index: 1423059 (The Pile)

Max Activating Token Index: 930

Text #1

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1416. Min Act: -0.0000

Data Index: 443103 (The Pile)

Max Activating Token Index: 221

Text #2

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1483. Min Act: -0.0001

Data Index: 1896012 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1367. Min Act: -0.0000

Data Index: 566207 (The Pile)

Max Activating Token Index: 836

Text #4

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1320. Min Act: -0.0000

Data Index: 1523118 (The Pile)

Max Activating Token Index: 423

Text #5

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1346. Min Act: -0.0000

Data Index: 366196 (The Pile)

Max Activating Token Index: 331

Text #6

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1329. Min Act: -0.0000

Data Index: 1527270 (The Pile)

Max Activating Token Index: 726

Text #7

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1436. Min Act: -0.0000

Data Index: 692587 (The Pile)

Max Activating Token Index: 892

Text #8

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1351. Min Act: -0.0001

Data Index: 843253 (The Pile)

Max Activating Token Index: 624

Text #9

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1283. Min Act: -0.0000

Data Index: 1487853 (The Pile)

Max Activating Token Index: 319

Text #10

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1234. Min Act: -0.0000

Data Index: 1458769 (The Pile)

Max Activating Token Index: 918

Text #11

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1231. Min Act: -0.0000

Data Index: 1349547 (The Pile)

Max Activating Token Index: 754

Text #12

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1205. Min Act: -0.0000

Data Index: 1781520 (The Pile)

Max Activating Token Index: 765

Text #13

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1206. Min Act: -0.0000

Data Index: 1775886 (The Pile)

Max Activating Token Index: 26

Text #14

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1302. Min Act: -0.0000

Data Index: 758319 (The Pile)

Max Activating Token Index: 73

Text #15

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1147. Min Act: -0.0001

Data Index: 240976 (The Pile)

Max Activating Token Index: 269

Text #16

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1157. Min Act: -0.0000

Data Index: 1794824 (The Pile)

Max Activating Token Index: 103

Text #17

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1161. Min Act: -0.0000

Data Index: 1699270 (The Pile)

Max Activating Token Index: 14

Text #18

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1083. Min Act: -0.0000

Data Index: 1406366 (The Pile)

Max Activating Token Index: 519

Text #19

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1062. Min Act: -0.0000

Data Index: 1687368 (The Pile)

Max Activating Token Index: 755