Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4254 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1621. Min Act: -0.0002

Data Index: 735540 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1547. Min Act: -0.0002

Data Index: 1240630 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1574. Min Act: -0.0002

Data Index: 1229636 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1350. Min Act: -0.0002

Data Index: 1279232 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1400. Min Act: -0.0002

Data Index: 1056684 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1330. Min Act: -0.0002

Data Index: 273649 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1640. Min Act: -0.0002

Data Index: 835202 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1422. Min Act: -0.0002

Data Index: 1035339 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1253. Min Act: -0.0002

Data Index: 1299671 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1211. Min Act: -0.0002

Data Index: 217321 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1339. Min Act: -0.0002

Data Index: 494807 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1303. Min Act: -0.0002

Data Index: 704061 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1377. Min Act: -0.0002

Data Index: 301890 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1252. Min Act: -0.0002

Data Index: 410745 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1297. Min Act: -0.0002

Data Index: 824090 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1231. Min Act: -0.0002

Data Index: 24389 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1273. Min Act: -0.0002

Data Index: 613768 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1192. Min Act: -0.0002

Data Index: 1155450 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1082. Min Act: -0.0002

Data Index: 1111544 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1433. Min Act: -0.0002

Data Index: 1117183 (C4 (Web Text))

Max Activating Token Index: 249