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

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

Neuron 459 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: 0.2902. Min Range: -0.2902

Max Act: 0.2902. Min Act: -0.0001

Data Index: 1075599 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1679. Min Act: -0.0000

Data Index: 682619 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1524. Min Act: -0.0000

Data Index: 68727 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1576. Min Act: -0.0001

Data Index: 991693 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1509. Min Act: -0.0000

Data Index: 704240 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1353. Min Act: -0.0000

Data Index: 1050698 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1304. Min Act: -0.0000

Data Index: 926122 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1377. Min Act: -0.0000

Data Index: 307263 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1318. Min Act: -0.0000

Data Index: 800797 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1406. Min Act: -0.0000

Data Index: 540338 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1369. Min Act: -0.0000

Data Index: 957926 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1343. Min Act: -0.0000

Data Index: 736085 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1363. Min Act: -0.0000

Data Index: 59485 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1348. Min Act: -0.0000

Data Index: 1153111 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1319. Min Act: -0.0000

Data Index: 811138 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1317. Min Act: -0.0000

Data Index: 119308 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1213. Min Act: -0.0000

Data Index: 1152406 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1251. Min Act: -0.0000

Data Index: 1008192 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1217. Min Act: -0.0000

Data Index: 77161 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1256. Min Act: -0.0000

Data Index: 925122 (C4 (Web Text))

Max Activating Token Index: 676