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

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

Neuron 276 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1435. Min Act: -0.0002

Data Index: 1307613 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1351. Min Act: -0.0002

Data Index: 616190 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1554. Min Act: -0.0002

Data Index: 756890 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1311. Min Act: -0.0002

Data Index: 498898 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1336. Min Act: -0.0002

Data Index: 1085611 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1201. Min Act: -0.0002

Data Index: 374166 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1294. Min Act: -0.0002

Data Index: 970268 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1288. Min Act: -0.0002

Data Index: 554949 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1322. Min Act: -0.0002

Data Index: 294011 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1179. Min Act: -0.0002

Data Index: 718022 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1217. Min Act: -0.0002

Data Index: 232762 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1278. Min Act: -0.0002

Data Index: 130079 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1098. Min Act: -0.0002

Data Index: 533405 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1319. Min Act: -0.0002

Data Index: 737263 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1238. Min Act: -0.0002

Data Index: 50498 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1182. Min Act: -0.0002

Data Index: 1102993 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1225. Min Act: -0.0002

Data Index: 827450 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1188. Min Act: -0.0002

Data Index: 1546489 (Python Code)

Max Activating Token Index: 392

Text #18

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1243. Min Act: -0.0002

Data Index: 551896 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1182. Min Act: -0.0002

Data Index: 1217607 (C4 (Web Text))

Max Activating Token Index: 174