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

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

Neuron 3705 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: 0.1531. Min Range: -0.1531

Max Act: 0.1531. Min Act: -0.0001

Data Index: 491660 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1422. Min Act: -0.0001

Data Index: 585729 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1467. Min Act: -0.0001

Data Index: 989292 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1383. Min Act: -0.0001

Data Index: 367301 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1495. Min Act: -0.0001

Data Index: 262734 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1370. Min Act: -0.0001

Data Index: 592222 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1495. Min Act: -0.0001

Data Index: 94472 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1275. Min Act: -0.0001

Data Index: 859513 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1398. Min Act: -0.0001

Data Index: 205864 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1255. Min Act: -0.0001

Data Index: 173210 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1319. Min Act: -0.0001

Data Index: 37365 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1406. Min Act: -0.0001

Data Index: 145371 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1360. Min Act: -0.0001

Data Index: 839383 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1401. Min Act: -0.0001

Data Index: 1048954 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1285. Min Act: -0.0001

Data Index: 865590 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1446. Min Act: -0.0001

Data Index: 1069250 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1329. Min Act: -0.0001

Data Index: 1035739 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1300. Min Act: -0.0002

Data Index: 179713 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1253. Min Act: -0.0001

Data Index: 815579 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1172. Min Act: -0.0001

Data Index: 151752 (C4 (Web Text))

Max Activating Token Index: 822