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

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

Neuron 2710 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1696. Min Act: -0.0001

Data Index: 1155950 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1621. Min Act: -0.0001

Data Index: 952964 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1592. Min Act: -0.0001

Data Index: 993078 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1397. Min Act: -0.0001

Data Index: 840538 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1481. Min Act: -0.0001

Data Index: 860042 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1494. Min Act: -0.0001

Data Index: 1136214 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1375. Min Act: -0.0001

Data Index: 458986 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1362. Min Act: -0.0001

Data Index: 1348704 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1313. Min Act: -0.0001

Data Index: 163296 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1351. Min Act: -0.0001

Data Index: 1036630 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1341. Min Act: -0.0001

Data Index: 308675 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1259. Min Act: -0.0001

Data Index: 159327 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1267. Min Act: -0.0001

Data Index: 1257014 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1201. Min Act: -0.0001

Data Index: 1155423 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1300. Min Act: -0.0001

Data Index: 1187442 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1474. Min Act: -0.0001

Data Index: 164549 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1142. Min Act: -0.0001

Data Index: 699001 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1271. Min Act: -0.0001

Data Index: 416111 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1229. Min Act: -0.0001

Data Index: 1084505 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1260. Min Act: -0.0001

Data Index: 267032 (C4 (Web Text))

Max Activating Token Index: 364