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

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

Neuron 3224 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0508. Min Act: -0.0002

Data Index: 42490 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0450. Min Act: -0.0002

Data Index: 127811 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0438. Min Act: -0.0002

Data Index: 150631 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0440. Min Act: -0.0002

Data Index: 783378 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0423. Min Act: -0.0002

Data Index: 726207 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0421. Min Act: -0.0002

Data Index: 404425 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1370371 (Python Code)

Max Activating Token Index: 919

Text #7

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0417. Min Act: -0.0002

Data Index: 533436 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1239803 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1461180 (Python Code)

Max Activating Token Index: 864

Text #10

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1088805 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1032250 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1302666 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0381. Min Act: -0.0002

Data Index: 254784 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0375. Min Act: -0.0002

Data Index: 1084675 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1435501 (Python Code)

Max Activating Token Index: 823

Text #16

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0369. Min Act: -0.0002

Data Index: 666964 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0358. Min Act: -0.0002

Data Index: 1151514 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0354. Min Act: -0.0002

Data Index: 256022 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0351. Min Act: -0.0002

Data Index: 387685 (C4 (Web Text))

Max Activating Token Index: 348