Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1449 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1591. Min Act: -0.0001

Data Index: 138669 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1551. Min Act: -0.0001

Data Index: 926410 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1480. Min Act: -0.0001

Data Index: 138637 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1360. Min Act: -0.0001

Data Index: 747123 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1386. Min Act: -0.0001

Data Index: 1507359 (Python Code)

Max Activating Token Index: 234

Text #5

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1416. Min Act: -0.0001

Data Index: 1618985 (Python Code)

Max Activating Token Index: 566

Text #6

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1328. Min Act: -0.0001

Data Index: 252237 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1331. Min Act: -0.0001

Data Index: 1053974 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1312. Min Act: -0.0001

Data Index: 1405471 (Python Code)

Max Activating Token Index: 263

Text #9

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1350. Min Act: -0.0001

Data Index: 607905 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1306. Min Act: -0.0001

Data Index: 419315 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1245. Min Act: -0.0001

Data Index: 1542346 (Python Code)

Max Activating Token Index: 556

Text #12

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1180. Min Act: -0.0001

Data Index: 1364832 (Python Code)

Max Activating Token Index: 867

Text #13

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1127687 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1258. Min Act: -0.0001

Data Index: 1511273 (Python Code)

Max Activating Token Index: 467

Text #15

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1401794 (Python Code)

Max Activating Token Index: 269

Text #16

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1233. Min Act: -0.0001

Data Index: 624456 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1214. Min Act: -0.0001

Data Index: 1401171 (Python Code)

Max Activating Token Index: 597

Text #18

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.0989. Min Act: -0.0001

Data Index: 836686 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1607963 (Python Code)

Max Activating Token Index: 542