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

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

Neuron 5751 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.2415. Min Act: -0.0000

Data Index: 957289 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1945. Min Act: -0.0000

Data Index: 1147695 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1807. Min Act: -0.0000

Data Index: 599628 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1609. Min Act: -0.0000

Data Index: 1445382 (Python Code)

Max Activating Token Index: 878

Text #4

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1511. Min Act: -0.0000

Data Index: 716134 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1487. Min Act: -0.0000

Data Index: 1181944 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1486. Min Act: -0.0000

Data Index: 1445776 (Python Code)

Max Activating Token Index: 902

Text #7

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1280. Min Act: -0.0000

Data Index: 644746 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1440. Min Act: -0.0000

Data Index: 351951 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1251. Min Act: -0.0000

Data Index: 1579186 (Python Code)

Max Activating Token Index: 222

Text #10

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1429. Min Act: -0.0000

Data Index: 537309 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1231. Min Act: -0.0000

Data Index: 1396468 (Python Code)

Max Activating Token Index: 422

Text #12

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1387. Min Act: -0.0000

Data Index: 1463244 (Python Code)

Max Activating Token Index: 389

Text #13

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1338. Min Act: -0.0000

Data Index: 1532658 (Python Code)

Max Activating Token Index: 540

Text #14

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1384. Min Act: -0.0000

Data Index: 360070 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1290. Min Act: -0.0000

Data Index: 1052771 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1349. Min Act: -0.0000

Data Index: 1323113 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1387. Min Act: -0.0000

Data Index: 1339299 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1247. Min Act: -0.0000

Data Index: 1626154 (Python Code)

Max Activating Token Index: 873

Text #19

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1142. Min Act: -0.0000

Data Index: 494698 (C4 (Web Text))

Max Activating Token Index: 785