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

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

Neuron 2219 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: 0.1670. Min Range: -0.1670

Max Act: 0.1670. Min Act: -0.0000

Data Index: 121689 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1615. Min Act: -0.0000

Data Index: 619731 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1335. Min Act: -0.0000

Data Index: 656955 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1446. Min Act: -0.0000

Data Index: 872456 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1141408 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1428. Min Act: -0.0000

Data Index: 639683 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1432. Min Act: -0.0000

Data Index: 496600 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1341. Min Act: -0.0000

Data Index: 421393 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1337. Min Act: -0.0000

Data Index: 101364 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1409. Min Act: -0.0000

Data Index: 804194 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1291. Min Act: -0.0000

Data Index: 44980 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1246. Min Act: -0.0000

Data Index: 614825 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1166. Min Act: -0.0000

Data Index: 1258703 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1244. Min Act: -0.0000

Data Index: 135657 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1278. Min Act: -0.0000

Data Index: 1019135 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1212. Min Act: -0.0000

Data Index: 490661 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1255. Min Act: -0.0000

Data Index: 1356304 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1288. Min Act: -0.0000

Data Index: 413365 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1203. Min Act: -0.0000

Data Index: 417136 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 0.1670. Min Range: -0.1670

Max Act: 0.1291. Min Act: -0.0000

Data Index: 222198 (C4 (Web Text))

Max Activating Token Index: 775