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

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

Neuron 2912 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: 0.1901. Min Range: -0.1901

Max Act: 0.1901. Min Act: -0.0000

Data Index: 129214 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1532. Min Act: -0.0000

Data Index: 429348 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1095650 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1505. Min Act: -0.0000

Data Index: 930096 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1557. Min Act: -0.0000

Data Index: 1165060 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1466. Min Act: -0.0000

Data Index: 350335 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1413. Min Act: -0.0000

Data Index: 819291 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1463. Min Act: -0.0000

Data Index: 702854 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1465. Min Act: -0.0000

Data Index: 604694 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1334. Min Act: -0.0000

Data Index: 803330 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1367. Min Act: -0.0000

Data Index: 556081 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1310. Min Act: -0.0000

Data Index: 222495 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1453. Min Act: -0.0000

Data Index: 980801 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1305. Min Act: -0.0000

Data Index: 373477 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1346. Min Act: -0.0000

Data Index: 608597 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1383. Min Act: -0.0000

Data Index: 401871 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1288. Min Act: -0.0001

Data Index: 194149 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1431. Min Act: -0.0000

Data Index: 531920 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1290. Min Act: -0.0000

Data Index: 143282 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 0.1901. Min Range: -0.1901

Max Act: 0.1323. Min Act: -0.0000

Data Index: 908155 (C4 (Web Text))

Max Activating Token Index: 587