Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2143 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1750. Min Act: -0.0001

Data Index: 1614115 (Python Code)

Max Activating Token Index: 671

Text #1

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1459. Min Act: -0.0001

Data Index: 1641597 (Python Code)

Max Activating Token Index: 1017

Text #2

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1359. Min Act: -0.0001

Data Index: 605920 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1452. Min Act: -0.0001

Data Index: 1624246 (Python Code)

Max Activating Token Index: 251

Text #4

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1396. Min Act: -0.0001

Data Index: 1389103 (Python Code)

Max Activating Token Index: 177

Text #5

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1346. Min Act: -0.0001

Data Index: 1510590 (Python Code)

Max Activating Token Index: 973

Text #6

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1437. Min Act: -0.0001

Data Index: 1508847 (Python Code)

Max Activating Token Index: 682

Text #7

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1286. Min Act: -0.0001

Data Index: 1414606 (Python Code)

Max Activating Token Index: 919

Text #8

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1257. Min Act: -0.0001

Data Index: 49605 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1242. Min Act: -0.0001

Data Index: 877902 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1263. Min Act: -0.0001

Data Index: 1545087 (Python Code)

Max Activating Token Index: 283

Text #11

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1215. Min Act: -0.0001

Data Index: 1489076 (Python Code)

Max Activating Token Index: 958

Text #12

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1468732 (Python Code)

Max Activating Token Index: 381

Text #13

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1199. Min Act: -0.0001

Data Index: 1045175 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1203. Min Act: -0.0001

Data Index: 1289241 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1122. Min Act: -0.0001

Data Index: 1625131 (Python Code)

Max Activating Token Index: 539

Text #16

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1124. Min Act: -0.0001

Data Index: 838956 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1143. Min Act: -0.0001

Data Index: 339946 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1126. Min Act: -0.0001

Data Index: 75429 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1121. Min Act: -0.0001

Data Index: 491147 (C4 (Web Text))

Max Activating Token Index: 736