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

Dataset: The Pile

Neuron 301 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1000225 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1590. Min Act: -0.0000

Data Index: 385680 (The Pile)

Max Activating Token Index: 260

Text #2

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1502. Min Act: -0.0000

Data Index: 677492 (The Pile)

Max Activating Token Index: 699

Text #3

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1490. Min Act: -0.0000

Data Index: 784723 (The Pile)

Max Activating Token Index: 542

Text #4

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1672. Min Act: -0.0000

Data Index: 543963 (The Pile)

Max Activating Token Index: 828

Text #5

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1539. Min Act: -0.0000

Data Index: 149610 (The Pile)

Max Activating Token Index: 241

Text #6

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1531. Min Act: -0.0000

Data Index: 235323 (The Pile)

Max Activating Token Index: 792

Text #7

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1365. Min Act: -0.0000

Data Index: 352906 (The Pile)

Max Activating Token Index: 766

Text #8

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1451. Min Act: -0.0000

Data Index: 796861 (The Pile)

Max Activating Token Index: 176

Text #9

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1535. Min Act: -0.0000

Data Index: 300849 (The Pile)

Max Activating Token Index: 406

Text #10

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1383. Min Act: -0.0000

Data Index: 261236 (The Pile)

Max Activating Token Index: 931

Text #11

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1322. Min Act: -0.0000

Data Index: 234194 (The Pile)

Max Activating Token Index: 584

Text #12

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1278. Min Act: -0.0000

Data Index: 303445 (The Pile)

Max Activating Token Index: 901

Text #13

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1348. Min Act: -0.0000

Data Index: 1045809 (The Pile)

Max Activating Token Index: 484

Text #14

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1390. Min Act: -0.0000

Data Index: 841277 (The Pile)

Max Activating Token Index: 475

Text #15

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1378. Min Act: -0.0000

Data Index: 1210471 (The Pile)

Max Activating Token Index: 346

Text #16

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1315. Min Act: -0.0000

Data Index: 1028345 (The Pile)

Max Activating Token Index: 150

Text #17

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1644. Min Act: -0.0000

Data Index: 1332835 (The Pile)

Max Activating Token Index: 915

Text #18

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1384. Min Act: -0.0000

Data Index: 779494 (The Pile)

Max Activating Token Index: 404

Text #19

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1341502 (The Pile)

Max Activating Token Index: 828