Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1643 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1722. Min Act: -0.0003

Data Index: 596085 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1405. Min Act: -0.0003

Data Index: 1276087 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1397. Min Act: -0.0003

Data Index: 132556 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1362. Min Act: -0.0003

Data Index: 1170729 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1397. Min Act: -0.0003

Data Index: 1184111 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1412. Min Act: -0.0003

Data Index: 1007603 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1378. Min Act: -0.0003

Data Index: 35601 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1317. Min Act: -0.0003

Data Index: 783256 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1230. Min Act: -0.0003

Data Index: 588875 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1314. Min Act: -0.0003

Data Index: 1191285 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1288. Min Act: -0.0003

Data Index: 378941 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1216. Min Act: -0.0003

Data Index: 447468 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1249. Min Act: -0.0003

Data Index: 851398 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1281. Min Act: -0.0003

Data Index: 988932 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1270. Min Act: -0.0003

Data Index: 1247692 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1200. Min Act: -0.0003

Data Index: 1268625 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1133. Min Act: -0.0003

Data Index: 803023 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1185. Min Act: -0.0003

Data Index: 256872 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1271. Min Act: -0.0003

Data Index: 929061 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1239. Min Act: -0.0003

Data Index: 918551 (C4 (Web Text))

Max Activating Token Index: 905