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

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

Neuron 2519 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3436. Min Act: -0.0000

Data Index: 837978 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2967. Min Act: -0.0001

Data Index: 1257803 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2354. Min Act: -0.0000

Data Index: 1139664 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1962. Min Act: -0.0001

Data Index: 1021792 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1567. Min Act: -0.0001

Data Index: 656962 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1764. Min Act: -0.0000

Data Index: 1149070 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1519. Min Act: -0.0001

Data Index: 58166 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1428. Min Act: -0.0000

Data Index: 1003339 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1533. Min Act: -0.0001

Data Index: 840282 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1414. Min Act: -0.0000

Data Index: 1338448 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1348. Min Act: -0.0000

Data Index: 383871 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1386. Min Act: -0.0001

Data Index: 1189113 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1472. Min Act: -0.0001

Data Index: 1072132 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1220. Min Act: -0.0001

Data Index: 797491 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1358. Min Act: -0.0001

Data Index: 849811 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1240. Min Act: -0.0001

Data Index: 886527 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1232865 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1270. Min Act: -0.0001

Data Index: 675798 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1207. Min Act: -0.0001

Data Index: 301120 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1295. Min Act: -0.0000

Data Index: 655873 (C4 (Web Text))

Max Activating Token Index: 565