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

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

Neuron 3969 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1868. Min Act: -0.0001

Data Index: 170180 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1884. Min Act: -0.0001

Data Index: 241911 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1829. Min Act: -0.0001

Data Index: 21540 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1682. Min Act: -0.0001

Data Index: 184779 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1653. Min Act: -0.0001

Data Index: 1190543 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1560. Min Act: -0.0001

Data Index: 213805 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1599. Min Act: -0.0001

Data Index: 1263202 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1591. Min Act: -0.0001

Data Index: 360941 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1592. Min Act: -0.0001

Data Index: 698870 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1570. Min Act: -0.0001

Data Index: 191194 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1327. Min Act: -0.0001

Data Index: 815443 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1565. Min Act: -0.0001

Data Index: 616863 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1504. Min Act: -0.0001

Data Index: 820655 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1431. Min Act: -0.0001

Data Index: 765523 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1542. Min Act: -0.0001

Data Index: 1203163 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1399. Min Act: -0.0001

Data Index: 1039494 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1388. Min Act: -0.0001

Data Index: 33455 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1296. Min Act: -0.0001

Data Index: 260030 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1535. Min Act: -0.0001

Data Index: 159655 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1530. Min Act: -0.0001

Data Index: 1069329 (C4 (Web Text))

Max Activating Token Index: 725