Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1636 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1706. Min Act: -0.0001

Data Index: 1370094 (Python Code)

Max Activating Token Index: 545

Text #1

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1552. Min Act: -0.0001

Data Index: 1327923 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1438. Min Act: -0.0001

Data Index: 1646018 (Python Code)

Max Activating Token Index: 655

Text #3

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1613. Min Act: -0.0001

Data Index: 1531074 (Python Code)

Max Activating Token Index: 897

Text #4

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1459. Min Act: -0.0000

Data Index: 342212 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1387. Min Act: -0.0001

Data Index: 1403407 (Python Code)

Max Activating Token Index: 477

Text #6

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1394113 (Python Code)

Max Activating Token Index: 820

Text #7

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1328. Min Act: -0.0001

Data Index: 214364 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1187. Min Act: -0.0001

Data Index: 1624763 (Python Code)

Max Activating Token Index: 989

Text #9

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1403. Min Act: -0.0001

Data Index: 1477954 (Python Code)

Max Activating Token Index: 837

Text #10

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1303. Min Act: -0.0001

Data Index: 1511205 (Python Code)

Max Activating Token Index: 741

Text #11

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1287. Min Act: -0.0001

Data Index: 1429721 (Python Code)

Max Activating Token Index: 564

Text #12

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1409. Min Act: -0.0001

Data Index: 1639141 (Python Code)

Max Activating Token Index: 504

Text #13

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1185. Min Act: -0.0001

Data Index: 1480951 (Python Code)

Max Activating Token Index: 888

Text #14

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1212. Min Act: -0.0001

Data Index: 1457371 (Python Code)

Max Activating Token Index: 658

Text #15

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1198. Min Act: -0.0001

Data Index: 477805 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1201. Min Act: -0.0000

Data Index: 158126 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1557416 (Python Code)

Max Activating Token Index: 352

Text #18

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1088. Min Act: -0.0001

Data Index: 311814 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.1706. Min Range: -0.1706

Max Act: 0.1312. Min Act: -0.0001

Data Index: 1629160 (Python Code)

Max Activating Token Index: 638