Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2009 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1761. Min Act: -0.0003

Data Index: 538806 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1338. Min Act: -0.0003

Data Index: 1211322 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1360. Min Act: -0.0002

Data Index: 29536 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1376. Min Act: -0.0003

Data Index: 309606 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1370. Min Act: -0.0003

Data Index: 935232 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1369. Min Act: -0.0003

Data Index: 116236 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1356. Min Act: -0.0003

Data Index: 529398 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1290. Min Act: -0.0004

Data Index: 26309 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1284. Min Act: -0.0002

Data Index: 1095034 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1236. Min Act: -0.0003

Data Index: 395299 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1278. Min Act: -0.0004

Data Index: 15541 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1228. Min Act: -0.0003

Data Index: 143892 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1265. Min Act: -0.0003

Data Index: 116616 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1266. Min Act: -0.0003

Data Index: 454238 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1252. Min Act: -0.0003

Data Index: 1301703 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1273. Min Act: -0.0003

Data Index: 966718 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1230. Min Act: -0.0003

Data Index: 1198144 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1235. Min Act: -0.0003

Data Index: 483642 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1274. Min Act: -0.0003

Data Index: 939949 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1230. Min Act: -0.0003

Data Index: 581144 (C4 (Web Text))

Max Activating Token Index: 325