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

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

Neuron 6 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1530. Min Act: -0.0001

Data Index: 1469614 (Python Code)

Max Activating Token Index: 658

Text #1

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1801. Min Act: -0.0001

Data Index: 1435461 (Python Code)

Max Activating Token Index: 768

Text #2

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1482. Min Act: -0.0001

Data Index: 1442636 (Python Code)

Max Activating Token Index: 820

Text #3

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1386. Min Act: -0.0001

Data Index: 1623344 (Python Code)

Max Activating Token Index: 404

Text #4

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1270. Min Act: -0.0001

Data Index: 1010266 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1432. Min Act: -0.0001

Data Index: 1489565 (Python Code)

Max Activating Token Index: 904

Text #6

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1345. Min Act: -0.0001

Data Index: 566246 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1278. Min Act: -0.0001

Data Index: 45269 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1193. Min Act: -0.0001

Data Index: 1260548 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1144. Min Act: -0.0001

Data Index: 1241118 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.0882. Min Act: -0.0001

Data Index: 1543319 (Python Code)

Max Activating Token Index: 315

Text #11

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1335. Min Act: -0.0001

Data Index: 405282 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1289. Min Act: -0.0001

Data Index: 1232704 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1282594 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1471519 (Python Code)

Max Activating Token Index: 716

Text #15

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1196. Min Act: -0.0001

Data Index: 1653271 (Python Code)

Max Activating Token Index: 338

Text #16

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1064. Min Act: -0.0001

Data Index: 1198134 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1174. Min Act: -0.0001

Data Index: 847913 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1194. Min Act: -0.0001

Data Index: 1166054 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1200. Min Act: -0.0001

Data Index: 859311 (C4 (Web Text))

Max Activating Token Index: 884