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

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

Neuron 5364 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6725. Min Range: -1.6725

Max Act: 1.6725. Min Act: -0.0000

Data Index: 532121 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 1.6725. Min Range: -1.6725

Max Act: 1.4611. Min Act: -0.0001

Data Index: 1228686 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 1.6725. Min Range: -1.6725

Max Act: 1.3827. Min Act: -0.0000

Data Index: 1019263 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 1.6725. Min Range: -1.6725

Max Act: 1.3851. Min Act: -0.0001

Data Index: 968973 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 1.6725. Min Range: -1.6725

Max Act: 1.2463. Min Act: -0.0000

Data Index: 1277042 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 1.6725. Min Range: -1.6725

Max Act: 1.1882. Min Act: -0.0000

Data Index: 1460663 (Python Code)

Max Activating Token Index: 968

Text #6

Max Range: 1.6725. Min Range: -1.6725

Max Act: 1.1420. Min Act: -0.0001

Data Index: 1194510 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 1.6725. Min Range: -1.6725

Max Act: 1.2238. Min Act: -0.0001

Data Index: 645897 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 1.6725. Min Range: -1.6725

Max Act: 1.1212. Min Act: -0.0000

Data Index: 93163 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 1.6725. Min Range: -1.6725

Max Act: 1.1177. Min Act: -0.0001

Data Index: 546082 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 1.6725. Min Range: -1.6725

Max Act: 1.2978. Min Act: -0.0000

Data Index: 1340573 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 1.6725. Min Range: -1.6725

Max Act: 1.1857. Min Act: -0.0000

Data Index: 16131 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 1.6725. Min Range: -1.6725

Max Act: 1.1561. Min Act: -0.0001

Data Index: 328040 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 1.6725. Min Range: -1.6725

Max Act: 0.9623. Min Act: -0.0001

Data Index: 1156329 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 1.6725. Min Range: -1.6725

Max Act: 1.0737. Min Act: -0.0001

Data Index: 599935 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 1.6725. Min Range: -1.6725

Max Act: 1.0407. Min Act: -0.0000

Data Index: 1377973 (Python Code)

Max Activating Token Index: 820

Text #16

Max Range: 1.6725. Min Range: -1.6725

Max Act: 1.0131. Min Act: -0.0000

Data Index: 1120004 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 1.6725. Min Range: -1.6725

Max Act: 1.0296. Min Act: -0.0000

Data Index: 802381 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 1.6725. Min Range: -1.6725

Max Act: 1.0682. Min Act: -0.0000

Data Index: 1603887 (Python Code)

Max Activating Token Index: 568

Text #19

Max Range: 1.6725. Min Range: -1.6725

Max Act: 1.0510. Min Act: -0.0000

Data Index: 412396 (C4 (Web Text))

Max Activating Token Index: 832