Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1485 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1319. Min Act: -0.0002

Data Index: 705719 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1293. Min Act: -0.0002

Data Index: 1000250 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1273. Min Act: -0.0002

Data Index: 1213784 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1234. Min Act: -0.0002

Data Index: 767759 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1260. Min Act: -0.0002

Data Index: 65528 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1254. Min Act: -0.0002

Data Index: 155838 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1215. Min Act: -0.0002

Data Index: 1144630 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1194. Min Act: -0.0002

Data Index: 127607 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1206. Min Act: -0.0002

Data Index: 909540 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1222. Min Act: -0.0002

Data Index: 450355 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1271. Min Act: -0.0002

Data Index: 1018559 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1181. Min Act: -0.0002

Data Index: 310030 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1148. Min Act: -0.0002

Data Index: 783106 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1141. Min Act: -0.0002

Data Index: 1331550 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1134. Min Act: -0.0002

Data Index: 1277916 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1118. Min Act: -0.0002

Data Index: 1517944 (Python Code)

Max Activating Token Index: 301

Text #16

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1090. Min Act: -0.0002

Data Index: 109810 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1005. Min Act: -0.0001

Data Index: 188103 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1126. Min Act: -0.0002

Data Index: 641851 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.1319. Min Range: -0.1319

Max Act: 0.1113. Min Act: -0.0002

Data Index: 463204 (C4 (Web Text))

Max Activating Token Index: 281