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

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

Neuron 3762 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1898. Min Act: -0.0000

Data Index: 716815 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1806. Min Act: -0.0001

Data Index: 508918 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1539. Min Act: -0.0001

Data Index: 975092 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1559. Min Act: -0.0001

Data Index: 1048221 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1550. Min Act: -0.0001

Data Index: 1063574 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1578. Min Act: -0.0000

Data Index: 942699 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1498. Min Act: -0.0001

Data Index: 716627 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1539. Min Act: -0.0000

Data Index: 815168 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1474. Min Act: -0.0000

Data Index: 188030 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1632. Min Act: -0.0001

Data Index: 667267 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1458. Min Act: -0.0001

Data Index: 222856 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1416. Min Act: -0.0001

Data Index: 462979 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1430. Min Act: -0.0001

Data Index: 166046 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1271. Min Act: -0.0001

Data Index: 683929 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1359. Min Act: -0.0001

Data Index: 89496 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1362. Min Act: -0.0001

Data Index: 179276 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1517. Min Act: -0.0001

Data Index: 147945 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1409. Min Act: -0.0001

Data Index: 583112 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1406. Min Act: -0.0001

Data Index: 742877 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1416. Min Act: -0.0001

Data Index: 322836 (C4 (Web Text))

Max Activating Token Index: 685