Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1423. Min Act: -0.0001

Data Index: 1331557 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1342. Min Act: -0.0001

Data Index: 74805 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1429. Min Act: -0.0001

Data Index: 1253866 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1410. Min Act: -0.0001

Data Index: 797605 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1358. Min Act: -0.0001

Data Index: 200849 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1280. Min Act: -0.0001

Data Index: 571853 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1313. Min Act: -0.0001

Data Index: 681380 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1291. Min Act: 0.0000

Data Index: 969357 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1286. Min Act: -0.0001

Data Index: 185872 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1224. Min Act: -0.0001

Data Index: 541489 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1265. Min Act: -0.0001

Data Index: 506481 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1207. Min Act: -0.0001

Data Index: 1455546 (Python Code)

Max Activating Token Index: 307

Text #12

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1229. Min Act: -0.0001

Data Index: 212953 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1256. Min Act: -0.0001

Data Index: 1152747 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1255. Min Act: -0.0000

Data Index: 1054930 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1253. Min Act: -0.0001

Data Index: 477098 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1249. Min Act: -0.0001

Data Index: 462748 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1252. Min Act: -0.0001

Data Index: 598912 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1064466 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1247. Min Act: -0.0001

Data Index: 425720 (C4 (Web Text))

Max Activating Token Index: 429