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

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

Neuron 589 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1960. Min Act: -0.0001

Data Index: 378945 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1854. Min Act: -0.0001

Data Index: 711593 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1711. Min Act: -0.0001

Data Index: 825285 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1436. Min Act: -0.0001

Data Index: 999630 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1835. Min Act: -0.0001

Data Index: 620250 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1751. Min Act: -0.0001

Data Index: 691523 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1715. Min Act: -0.0001

Data Index: 1083917 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1457. Min Act: -0.0001

Data Index: 1086041 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1174. Min Act: -0.0001

Data Index: 316887 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1540. Min Act: -0.0001

Data Index: 1313253 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1432. Min Act: -0.0001

Data Index: 310516 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1287. Min Act: -0.0001

Data Index: 1089199 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1345. Min Act: -0.0001

Data Index: 780711 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1233. Min Act: -0.0001

Data Index: 905122 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1479. Min Act: -0.0001

Data Index: 1274021 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1367. Min Act: -0.0001

Data Index: 319254 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1210. Min Act: -0.0001

Data Index: 1050472 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1238. Min Act: -0.0001

Data Index: 321998 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1095. Min Act: -0.0001

Data Index: 611683 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1324. Min Act: -0.0001

Data Index: 983614 (C4 (Web Text))

Max Activating Token Index: 376