Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 544 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1561. Min Act: -0.0002

Data Index: 1122034 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1509. Min Act: -0.0002

Data Index: 681115 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1435. Min Act: -0.0001

Data Index: 879743 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1379. Min Act: -0.0002

Data Index: 1122624 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1406. Min Act: -0.0002

Data Index: 160448 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1383. Min Act: -0.0001

Data Index: 427617 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1434. Min Act: -0.0002

Data Index: 777500 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1424. Min Act: -0.0002

Data Index: 1062273 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1332. Min Act: -0.0001

Data Index: 62023 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1361. Min Act: -0.0001

Data Index: 68358 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1327. Min Act: -0.0001

Data Index: 707153 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1329. Min Act: -0.0002

Data Index: 261274 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1335. Min Act: -0.0001

Data Index: 1219731 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1267. Min Act: -0.0001

Data Index: 138587 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1115712 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1081071 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1260. Min Act: -0.0002

Data Index: 185970 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1309. Min Act: -0.0001

Data Index: 583632 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1261. Min Act: -0.0002

Data Index: 34839 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 0.1561. Min Range: -0.1561

Max Act: 0.1249. Min Act: -0.0002

Data Index: 768915 (C4 (Web Text))

Max Activating Token Index: 328