Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3574 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1420. Min Act: -0.0000

Data Index: 1487641 (Python Code)

Max Activating Token Index: 770

Text #1

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1573. Min Act: -0.0000

Data Index: 1046105 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1486. Min Act: -0.0000

Data Index: 937851 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1514. Min Act: 0.0000

Data Index: 403558 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1429. Min Act: -0.0000

Data Index: 631097 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1385. Min Act: -0.0000

Data Index: 1466233 (Python Code)

Max Activating Token Index: 349

Text #6

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1335. Min Act: -0.0000

Data Index: 753139 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1374. Min Act: 0.0000

Data Index: 504971 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1362. Min Act: -0.0000

Data Index: 763109 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1318. Min Act: -0.0000

Data Index: 1238325 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1317. Min Act: 0.0000

Data Index: 1134054 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1368. Min Act: -0.0000

Data Index: 1418830 (Python Code)

Max Activating Token Index: 542

Text #12

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1320. Min Act: -0.0000

Data Index: 676214 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1280. Min Act: -0.0000

Data Index: 1537595 (Python Code)

Max Activating Token Index: 192

Text #14

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1344. Min Act: -0.0000

Data Index: 701695 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1216. Min Act: -0.0000

Data Index: 1118654 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1309. Min Act: 0.0000

Data Index: 1583114 (Python Code)

Max Activating Token Index: 623

Text #17

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1317. Min Act: -0.0000

Data Index: 211884 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1257. Min Act: 0.0000

Data Index: 135924 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1196. Min Act: -0.0000

Data Index: 830445 (C4 (Web Text))

Max Activating Token Index: 383