Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3044 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1892. Min Act: -0.0001

Data Index: 956604 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1635. Min Act: -0.0001

Data Index: 197594 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1491. Min Act: -0.0001

Data Index: 1176944 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1472. Min Act: -0.0001

Data Index: 721919 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1559. Min Act: -0.0001

Data Index: 1127410 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1418. Min Act: -0.0001

Data Index: 1270992 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1348. Min Act: -0.0001

Data Index: 1263926 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1371. Min Act: -0.0001

Data Index: 1201659 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1486. Min Act: -0.0001

Data Index: 22295 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1367. Min Act: -0.0001

Data Index: 614624 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1353. Min Act: -0.0001

Data Index: 965100 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1405. Min Act: -0.0001

Data Index: 573680 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1473. Min Act: -0.0001

Data Index: 693149 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1369. Min Act: -0.0001

Data Index: 658284 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1327. Min Act: -0.0001

Data Index: 194974 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1364. Min Act: -0.0001

Data Index: 52012 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1275. Min Act: -0.0001

Data Index: 450273 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1354. Min Act: -0.0001

Data Index: 998910 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1287. Min Act: -0.0001

Data Index: 276571 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1380. Min Act: -0.0001

Data Index: 435677 (C4 (Web Text))

Max Activating Token Index: 723