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

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

Neuron 3354 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.9508. Min Act: 0.0000

Data Index: 840347 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8152. Min Act: -0.0000

Data Index: 1411243 (Python Code)

Max Activating Token Index: 712

Text #2

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7279. Min Act: -0.0000

Data Index: 1384977 (Python Code)

Max Activating Token Index: 319

Text #3

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7156. Min Act: -0.0000

Data Index: 1455874 (Python Code)

Max Activating Token Index: 556

Text #4

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1619135 (Python Code)

Max Activating Token Index: 786

Text #5

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6754. Min Act: -0.0000

Data Index: 1472376 (Python Code)

Max Activating Token Index: 448

Text #6

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6710. Min Act: -0.0000

Data Index: 913779 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6330. Min Act: -0.0000

Data Index: 43832 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6713. Min Act: -0.0000

Data Index: 699575 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6666. Min Act: 0.0000

Data Index: 820940 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6658. Min Act: -0.0000

Data Index: 1395310 (Python Code)

Max Activating Token Index: 307

Text #11

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6385. Min Act: -0.0000

Data Index: 1568149 (Python Code)

Max Activating Token Index: 812

Text #12

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6530. Min Act: -0.0000

Data Index: 1439555 (Python Code)

Max Activating Token Index: 385

Text #13

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6414. Min Act: -0.0000

Data Index: 74576 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1459553 (Python Code)

Max Activating Token Index: 734

Text #15

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.7009. Min Act: 0.0000

Data Index: 461133 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6386. Min Act: -0.0000

Data Index: 956790 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6046. Min Act: 0.0000

Data Index: 1390694 (Python Code)

Max Activating Token Index: 844

Text #18

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1012301 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.9508. Min Range: -0.9508

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1199045 (C4 (Web Text))

Max Activating Token Index: 713