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

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

Neuron 3590 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1734. Min Act: -0.0002

Data Index: 153162 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1701. Min Act: -0.0002

Data Index: 473155 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1630. Min Act: -0.0002

Data Index: 783407 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1564. Min Act: -0.0002

Data Index: 741077 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1412. Min Act: -0.0002

Data Index: 995198 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1348. Min Act: -0.0002

Data Index: 558010 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1489. Min Act: -0.0002

Data Index: 1246522 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1385. Min Act: -0.0002

Data Index: 922916 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1340. Min Act: -0.0002

Data Index: 998220 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1413. Min Act: -0.0002

Data Index: 1086599 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1360. Min Act: -0.0002

Data Index: 55494 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1305. Min Act: -0.0002

Data Index: 384855 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1296. Min Act: -0.0002

Data Index: 301139 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1289. Min Act: -0.0002

Data Index: 918680 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1236. Min Act: -0.0002

Data Index: 526928 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1413. Min Act: -0.0002

Data Index: 1118722 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1270. Min Act: -0.0002

Data Index: 916194 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1268. Min Act: -0.0002

Data Index: 484570 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1186. Min Act: -0.0002

Data Index: 1073969 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1339. Min Act: -0.0002

Data Index: 1170384 (C4 (Web Text))

Max Activating Token Index: 192