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

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

Neuron 6005 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1623. Min Act: -0.0002

Data Index: 1182309 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1368. Min Act: -0.0002

Data Index: 553567 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1396. Min Act: -0.0003

Data Index: 1186183 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1377. Min Act: -0.0002

Data Index: 1266172 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1370. Min Act: -0.0002

Data Index: 236945 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1360. Min Act: -0.0002

Data Index: 1030324 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1350. Min Act: -0.0002

Data Index: 285026 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1312. Min Act: -0.0002

Data Index: 688997 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1318. Min Act: -0.0002

Data Index: 784457 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1295. Min Act: -0.0002

Data Index: 1156645 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1336. Min Act: -0.0002

Data Index: 1079898 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1284. Min Act: -0.0002

Data Index: 1239880 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1294. Min Act: -0.0002

Data Index: 1112171 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1303. Min Act: -0.0002

Data Index: 1024605 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1277. Min Act: -0.0002

Data Index: 1104974 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1300. Min Act: -0.0002

Data Index: 78407 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1265. Min Act: -0.0002

Data Index: 791590 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1260. Min Act: -0.0002

Data Index: 1109316 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1287. Min Act: -0.0002

Data Index: 329822 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1280. Min Act: -0.0002

Data Index: 961376 (C4 (Web Text))

Max Activating Token Index: 233