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

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

Neuron 4381 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1540. Min Act: -0.0001

Data Index: 363939 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1467. Min Act: -0.0001

Data Index: 1120717 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1417. Min Act: -0.0001

Data Index: 842698 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1399. Min Act: -0.0002

Data Index: 65217 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1384. Min Act: -0.0001

Data Index: 131161 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1383. Min Act: -0.0001

Data Index: 1352878 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1383. Min Act: -0.0001

Data Index: 441734 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1505. Min Act: -0.0001

Data Index: 1219825 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1348. Min Act: -0.0001

Data Index: 389033 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1328. Min Act: -0.0001

Data Index: 282090 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1325. Min Act: -0.0001

Data Index: 358713 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1414. Min Act: -0.0001

Data Index: 808083 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1269. Min Act: -0.0001

Data Index: 1244803 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1258. Min Act: -0.0001

Data Index: 1214352 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1262. Min Act: -0.0001

Data Index: 233312 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1250. Min Act: -0.0001

Data Index: 69756 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1273. Min Act: -0.0001

Data Index: 160767 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1295. Min Act: -0.0001

Data Index: 1078589 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1298. Min Act: -0.0001

Data Index: 228917 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1242. Min Act: -0.0001

Data Index: 1124975 (C4 (Web Text))

Max Activating Token Index: 543