Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1318 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1255. Min Act: -0.0001

Data Index: 948986 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1291. Min Act: -0.0002

Data Index: 727812 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1232. Min Act: -0.0001

Data Index: 504842 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1283. Min Act: -0.0002

Data Index: 1299402 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1260. Min Act: -0.0002

Data Index: 900821 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1263. Min Act: -0.0002

Data Index: 183753 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1257. Min Act: -0.0001

Data Index: 165055 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1332. Min Act: -0.0001

Data Index: 757354 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1351. Min Act: -0.0001

Data Index: 427777 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1219. Min Act: -0.0001

Data Index: 512637 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1181. Min Act: -0.0002

Data Index: 1246037 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1174. Min Act: -0.0001

Data Index: 549792 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1139. Min Act: -0.0001

Data Index: 934729 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1126. Min Act: -0.0001

Data Index: 826337 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1254. Min Act: -0.0001

Data Index: 256005 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1164. Min Act: -0.0002

Data Index: 613622 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1147. Min Act: -0.0002

Data Index: 673103 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1100. Min Act: -0.0001

Data Index: 923143 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1174. Min Act: -0.0002

Data Index: 883199 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1171. Min Act: -0.0002

Data Index: 217276 (C4 (Web Text))

Max Activating Token Index: 908