Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3400 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1849. Min Act: -0.0002

Data Index: 336573 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1675. Min Act: -0.0001

Data Index: 1151876 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1637. Min Act: -0.0001

Data Index: 670809 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1582. Min Act: -0.0001

Data Index: 101193 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1469. Min Act: -0.0001

Data Index: 249250 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1355. Min Act: -0.0001

Data Index: 1079615 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1612. Min Act: -0.0001

Data Index: 507460 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1435. Min Act: -0.0001

Data Index: 199336 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1398. Min Act: -0.0001

Data Index: 733821 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1385. Min Act: -0.0001

Data Index: 468940 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1331. Min Act: -0.0001

Data Index: 856627 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1325. Min Act: -0.0001

Data Index: 846403 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1355. Min Act: -0.0001

Data Index: 128883 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1370. Min Act: -0.0001

Data Index: 184443 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1278. Min Act: -0.0001

Data Index: 601208 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1187. Min Act: -0.0001

Data Index: 873345 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1365. Min Act: -0.0001

Data Index: 1262300 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1217. Min Act: -0.0001

Data Index: 850941 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1382. Min Act: -0.0001

Data Index: 241510 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1372. Min Act: -0.0001

Data Index: 493741 (C4 (Web Text))

Max Activating Token Index: 256