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

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

Neuron 732 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1653. Min Act: -0.0001

Data Index: 726779 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1629. Min Act: -0.0001

Data Index: 983515 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1625. Min Act: -0.0001

Data Index: 498732 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1475. Min Act: -0.0001

Data Index: 1076084 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1551. Min Act: -0.0001

Data Index: 324811 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1540. Min Act: -0.0001

Data Index: 976925 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1399. Min Act: -0.0001

Data Index: 36115 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1428. Min Act: -0.0001

Data Index: 1275942 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1378. Min Act: -0.0001

Data Index: 907801 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1474. Min Act: -0.0001

Data Index: 513975 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1382. Min Act: -0.0001

Data Index: 973241 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1368. Min Act: -0.0001

Data Index: 744345 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1281. Min Act: -0.0001

Data Index: 706558 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1301. Min Act: -0.0001

Data Index: 663037 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1178. Min Act: -0.0001

Data Index: 1026912 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1193. Min Act: -0.0001

Data Index: 879295 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1131. Min Act: -0.0001

Data Index: 519808 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1136. Min Act: -0.0001

Data Index: 575952 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1197. Min Act: -0.0001

Data Index: 706580 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1150. Min Act: -0.0001

Data Index: 1122353 (C4 (Web Text))

Max Activating Token Index: 154