Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 638 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1510. Min Act: -0.0003

Data Index: 1252315 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1420. Min Act: -0.0003

Data Index: 959889 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1288. Min Act: -0.0003

Data Index: 1269369 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1271. Min Act: -0.0003

Data Index: 686168 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1296. Min Act: -0.0003

Data Index: 48405 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1244. Min Act: -0.0003

Data Index: 976476 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1181. Min Act: -0.0002

Data Index: 39477 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1198. Min Act: -0.0003

Data Index: 756920 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1200. Min Act: -0.0003

Data Index: 534163 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1185. Min Act: -0.0003

Data Index: 233533 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1086. Min Act: -0.0003

Data Index: 106290 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1066. Min Act: -0.0002

Data Index: 1353908 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1051. Min Act: -0.0003

Data Index: 964665 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1017. Min Act: -0.0003

Data Index: 1318097 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1012. Min Act: -0.0003

Data Index: 559776 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.0989. Min Act: -0.0003

Data Index: 111162 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.0978. Min Act: -0.0003

Data Index: 1338226 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1012. Min Act: -0.0003

Data Index: 458847 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.0975. Min Act: -0.0002

Data Index: 400099 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.0959. Min Act: -0.0003

Data Index: 188255 (C4 (Web Text))

Max Activating Token Index: 930