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

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

Neuron 5066 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.1382. Min Act: -0.0000

Data Index: 1642555 (Python Code)

Max Activating Token Index: 868

Text #1

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.1425. Min Act: -0.0000

Data Index: 1570066 (Python Code)

Max Activating Token Index: 602

Text #2

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.2322. Min Act: -0.0000

Data Index: 1430746 (Python Code)

Max Activating Token Index: 501

Text #3

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.1532. Min Act: -0.0000

Data Index: 1584689 (Python Code)

Max Activating Token Index: 778

Text #4

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.1411. Min Act: -0.0000

Data Index: 1646419 (Python Code)

Max Activating Token Index: 895

Text #5

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0992. Min Act: -0.0000

Data Index: 1647360 (Python Code)

Max Activating Token Index: 466

Text #6

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.9847. Min Act: -0.0000

Data Index: 1624230 (Python Code)

Max Activating Token Index: 817

Text #7

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.1418. Min Act: -0.0000

Data Index: 1457553 (Python Code)

Max Activating Token Index: 317

Text #8

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0078. Min Act: -0.0000

Data Index: 1420060 (Python Code)

Max Activating Token Index: 450

Text #9

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0584. Min Act: -0.0000

Data Index: 1545630 (Python Code)

Max Activating Token Index: 537

Text #10

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0197. Min Act: -0.0000

Data Index: 1641615 (Python Code)

Max Activating Token Index: 372

Text #11

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0048. Min Act: -0.0000

Data Index: 1622997 (Python Code)

Max Activating Token Index: 554

Text #12

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.9795. Min Act: -0.0000

Data Index: 1628933 (Python Code)

Max Activating Token Index: 1022

Text #13

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0302. Min Act: -0.0000

Data Index: 1377794 (Python Code)

Max Activating Token Index: 447

Text #14

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0182. Min Act: -0.0000

Data Index: 1544604 (Python Code)

Max Activating Token Index: 440

Text #15

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0098. Min Act: -0.0000

Data Index: 1644161 (Python Code)

Max Activating Token Index: 647

Text #16

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.9930. Min Act: -0.0000

Data Index: 1521875 (Python Code)

Max Activating Token Index: 995

Text #17

Max Range: 1.2322. Min Range: -1.2322

Max Act: 1.0225. Min Act: -0.0000

Data Index: 1407563 (Python Code)

Max Activating Token Index: 676

Text #18

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1409249 (Python Code)

Max Activating Token Index: 807

Text #19

Max Range: 1.2322. Min Range: -1.2322

Max Act: 0.9700. Min Act: -0.0000

Data Index: 1570995 (Python Code)

Max Activating Token Index: 1006