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

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

Neuron 1489 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1564. Min Act: -0.0001

Data Index: 948295 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1422. Min Act: -0.0001

Data Index: 219958 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1455. Min Act: -0.0001

Data Index: 1079429 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1469. Min Act: -0.0001

Data Index: 67081 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1458. Min Act: -0.0001

Data Index: 182517 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1497. Min Act: -0.0001

Data Index: 667249 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1440. Min Act: -0.0000

Data Index: 1073230 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1359. Min Act: -0.0001

Data Index: 1270788 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1419. Min Act: -0.0001

Data Index: 310238 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1455. Min Act: -0.0001

Data Index: 1206528 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1398. Min Act: -0.0001

Data Index: 1332711 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1394. Min Act: -0.0000

Data Index: 730110 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1385. Min Act: -0.0001

Data Index: 1246036 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1371. Min Act: -0.0000

Data Index: 255173 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1352. Min Act: -0.0001

Data Index: 85685 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1349. Min Act: -0.0001

Data Index: 170721 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1344. Min Act: -0.0000

Data Index: 518052 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1380. Min Act: -0.0001

Data Index: 883236 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1335. Min Act: -0.0001

Data Index: 1122752 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1331. Min Act: -0.0001

Data Index: 403813 (C4 (Web Text))

Max Activating Token Index: 22