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

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

Neuron 3075 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1528. Min Act: -0.0001

Data Index: 1334240 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1589. Min Act: -0.0001

Data Index: 626613 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1502. Min Act: -0.0000

Data Index: 490403 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1372. Min Act: -0.0001

Data Index: 498073 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1436. Min Act: -0.0001

Data Index: 52243 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1328. Min Act: -0.0001

Data Index: 372295 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1366. Min Act: -0.0001

Data Index: 891302 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1404. Min Act: -0.0001

Data Index: 351434 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1349. Min Act: -0.0001

Data Index: 413139 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1293. Min Act: -0.0001

Data Index: 65091 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1333. Min Act: -0.0001

Data Index: 435267 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1389. Min Act: -0.0001

Data Index: 645456 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1388. Min Act: -0.0001

Data Index: 303537 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1331. Min Act: -0.0001

Data Index: 190096 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1383. Min Act: -0.0001

Data Index: 1216057 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1276. Min Act: -0.0001

Data Index: 198181 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1322. Min Act: -0.0001

Data Index: 872835 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1316. Min Act: -0.0001

Data Index: 988235 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1368. Min Act: -0.0001

Data Index: 948863 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1362. Min Act: -0.0001

Data Index: 38318 (C4 (Web Text))

Max Activating Token Index: 62