Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4257 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1881. Min Act: -0.0001

Data Index: 164517 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1634. Min Act: -0.0001

Data Index: 953499 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1685. Min Act: -0.0001

Data Index: 1288650 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1556. Min Act: -0.0001

Data Index: 824350 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1535. Min Act: -0.0001

Data Index: 1196508 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1558. Min Act: -0.0001

Data Index: 1314879 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1594. Min Act: -0.0000

Data Index: 835527 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1644. Min Act: -0.0001

Data Index: 276279 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1584. Min Act: -0.0001

Data Index: 1115917 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1485. Min Act: -0.0001

Data Index: 13416 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1405217 (Python Code)

Max Activating Token Index: 202

Text #11

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1472. Min Act: -0.0001

Data Index: 594034 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1538. Min Act: -0.0001

Data Index: 741372 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1543. Min Act: -0.0001

Data Index: 745062 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1538. Min Act: -0.0001

Data Index: 176008 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1308. Min Act: -0.0001

Data Index: 1005897 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1512. Min Act: -0.0001

Data Index: 435751 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1381. Min Act: -0.0001

Data Index: 337749 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1295. Min Act: -0.0001

Data Index: 1575416 (Python Code)

Max Activating Token Index: 226

Text #19

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1567. Min Act: -0.0001

Data Index: 1404227 (Python Code)

Max Activating Token Index: 822