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

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

Neuron 5481 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1697. Min Act: -0.0000

Data Index: 1487601 (Python Code)

Max Activating Token Index: 981

Text #1

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1439. Min Act: -0.0000

Data Index: 1557089 (Python Code)

Max Activating Token Index: 395

Text #2

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1550. Min Act: -0.0001

Data Index: 1395829 (Python Code)

Max Activating Token Index: 640

Text #3

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1378. Min Act: -0.0000

Data Index: 1511265 (Python Code)

Max Activating Token Index: 759

Text #4

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1548. Min Act: -0.0000

Data Index: 393659 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1384884 (Python Code)

Max Activating Token Index: 307

Text #6

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1531. Min Act: -0.0001

Data Index: 1504897 (Python Code)

Max Activating Token Index: 371

Text #7

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1280. Min Act: -0.0000

Data Index: 584805 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1309. Min Act: -0.0000

Data Index: 1564404 (Python Code)

Max Activating Token Index: 584

Text #9

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1210. Min Act: -0.0001

Data Index: 162956 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1277. Min Act: -0.0000

Data Index: 517381 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1134. Min Act: -0.0001

Data Index: 207743 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1195. Min Act: -0.0000

Data Index: 12493 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1111. Min Act: -0.0000

Data Index: 729345 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1177. Min Act: -0.0000

Data Index: 1462303 (Python Code)

Max Activating Token Index: 861

Text #15

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1119. Min Act: -0.0000

Data Index: 1061858 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1100. Min Act: -0.0000

Data Index: 955619 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1183. Min Act: -0.0000

Data Index: 216819 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1129. Min Act: -0.0001

Data Index: 1545486 (Python Code)

Max Activating Token Index: 518

Text #19

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1161. Min Act: -0.0000

Data Index: 207602 (C4 (Web Text))

Max Activating Token Index: 552