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

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

Neuron 1383 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1662. Min Act: -0.0000

Data Index: 181637 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1576. Min Act: -0.0000

Data Index: 1079036 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1556. Min Act: -0.0000

Data Index: 460800 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1424. Min Act: -0.0000

Data Index: 916964 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1419. Min Act: -0.0000

Data Index: 543268 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1358. Min Act: -0.0000

Data Index: 229253 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1286162 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1326280 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1382. Min Act: -0.0000

Data Index: 1021564 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1251. Min Act: -0.0000

Data Index: 279837 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1296. Min Act: -0.0000

Data Index: 562960 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1283. Min Act: -0.0000

Data Index: 566929 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1246. Min Act: -0.0000

Data Index: 994272 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1208. Min Act: -0.0000

Data Index: 165290 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1155. Min Act: -0.0000

Data Index: 842617 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1221. Min Act: -0.0000

Data Index: 1076003 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1206. Min Act: -0.0000

Data Index: 357522 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1111. Min Act: -0.0000

Data Index: 1134090 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1130. Min Act: -0.0000

Data Index: 1343907 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 0.1662. Min Range: -0.1662

Max Act: 0.1117. Min Act: -0.0000

Data Index: 976360 (C4 (Web Text))

Max Activating Token Index: 85