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

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

Neuron 1847 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1751. Min Act: -0.0001

Data Index: 979509 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1625. Min Act: -0.0000

Data Index: 822113 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1571. Min Act: -0.0000

Data Index: 498255 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1551. Min Act: -0.0000

Data Index: 346582 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1430. Min Act: -0.0000

Data Index: 1339518 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1436. Min Act: -0.0000

Data Index: 1328290 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1432. Min Act: -0.0000

Data Index: 270214 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1297. Min Act: -0.0000

Data Index: 633662 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1347. Min Act: -0.0000

Data Index: 770349 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1322. Min Act: -0.0000

Data Index: 1340823 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1375. Min Act: -0.0000

Data Index: 1023179 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1321. Min Act: -0.0000

Data Index: 458332 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1329. Min Act: -0.0000

Data Index: 1200941 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1267. Min Act: -0.0000

Data Index: 1359578 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1264. Min Act: -0.0000

Data Index: 1138922 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1246. Min Act: -0.0000

Data Index: 608822 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1237. Min Act: -0.0000

Data Index: 625901 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1269. Min Act: -0.0000

Data Index: 978591 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1327. Min Act: -0.0000

Data Index: 1152210 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1308. Min Act: -0.0000

Data Index: 804560 (C4 (Web Text))

Max Activating Token Index: 302