Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1154 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1746. Min Act: -0.0000

Data Index: 1211609 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1665. Min Act: -0.0000

Data Index: 777690 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1148962 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1339. Min Act: -0.0000

Data Index: 961307 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1438. Min Act: -0.0000

Data Index: 524037 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1405. Min Act: -0.0000

Data Index: 1108624 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1394. Min Act: -0.0000

Data Index: 261475 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1393. Min Act: -0.0000

Data Index: 324036 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1355. Min Act: -0.0000

Data Index: 972538 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1059954 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1333. Min Act: -0.0000

Data Index: 1285246 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1400. Min Act: -0.0000

Data Index: 13547 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1266. Min Act: -0.0000

Data Index: 627160 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1391. Min Act: -0.0000

Data Index: 1289183 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1249. Min Act: -0.0000

Data Index: 315066 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1219. Min Act: -0.0000

Data Index: 569880 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1263. Min Act: -0.0000

Data Index: 1071212 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1261. Min Act: -0.0000

Data Index: 1207257 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1193. Min Act: -0.0000

Data Index: 810339 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1190. Min Act: -0.0000

Data Index: 316014 (C4 (Web Text))

Max Activating Token Index: 248