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

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

Neuron 98 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1548. Min Act: -0.0001

Data Index: 1623361 (Python Code)

Max Activating Token Index: 52

Text #1

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1464. Min Act: -0.0001

Data Index: 1400665 (Python Code)

Max Activating Token Index: 546

Text #2

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1177. Min Act: -0.0001

Data Index: 1515826 (Python Code)

Max Activating Token Index: 517

Text #3

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1241. Min Act: -0.0001

Data Index: 1386182 (Python Code)

Max Activating Token Index: 941

Text #4

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1044. Min Act: -0.0001

Data Index: 1497581 (Python Code)

Max Activating Token Index: 507

Text #5

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1240. Min Act: -0.0001

Data Index: 1566599 (Python Code)

Max Activating Token Index: 314

Text #6

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1481482 (Python Code)

Max Activating Token Index: 162

Text #7

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.0975. Min Act: -0.0001

Data Index: 1560328 (Python Code)

Max Activating Token Index: 41

Text #8

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1122. Min Act: -0.0001

Data Index: 1426366 (Python Code)

Max Activating Token Index: 119

Text #9

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1129. Min Act: -0.0001

Data Index: 1365264 (Python Code)

Max Activating Token Index: 297

Text #10

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.0890. Min Act: -0.0001

Data Index: 1533664 (Python Code)

Max Activating Token Index: 323

Text #11

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1027. Min Act: -0.0001

Data Index: 1523498 (Python Code)

Max Activating Token Index: 108

Text #12

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1035. Min Act: -0.0001

Data Index: 1442072 (Python Code)

Max Activating Token Index: 25

Text #13

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.0997. Min Act: -0.0001

Data Index: 1562353 (Python Code)

Max Activating Token Index: 395

Text #14

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1062. Min Act: -0.0001

Data Index: 1473189 (Python Code)

Max Activating Token Index: 352

Text #15

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1012. Min Act: -0.0001

Data Index: 1410417 (Python Code)

Max Activating Token Index: 341

Text #16

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1002. Min Act: -0.0001

Data Index: 1484812 (Python Code)

Max Activating Token Index: 15

Text #17

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.0983. Min Act: -0.0001

Data Index: 1384093 (Python Code)

Max Activating Token Index: 288

Text #18

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1020. Min Act: -0.0001

Data Index: 1431895 (Python Code)

Max Activating Token Index: 1013

Text #19

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.0881. Min Act: -0.0001

Data Index: 1650261 (Python Code)

Max Activating Token Index: 664