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

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

Neuron 4550 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2541. Min Act: -0.0001

Data Index: 449246 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2039. Min Act: -0.0001

Data Index: 1138012 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1538. Min Act: -0.0001

Data Index: 632376 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1494. Min Act: -0.0001

Data Index: 1060938 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1715. Min Act: -0.0001

Data Index: 363536 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1524. Min Act: -0.0001

Data Index: 267749 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1521. Min Act: -0.0001

Data Index: 131572 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1449. Min Act: -0.0002

Data Index: 721647 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1385. Min Act: -0.0001

Data Index: 213390 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1419. Min Act: -0.0001

Data Index: 622638 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1403. Min Act: -0.0001

Data Index: 1232918 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1381. Min Act: -0.0001

Data Index: 475077 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1365. Min Act: -0.0001

Data Index: 465045 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1457. Min Act: -0.0001

Data Index: 628430 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1363. Min Act: -0.0001

Data Index: 733454 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1508. Min Act: -0.0001

Data Index: 1276112 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1315. Min Act: -0.0001

Data Index: 379564 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1232. Min Act: -0.0001

Data Index: 488642 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1019265 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1333. Min Act: -0.0001

Data Index: 123474 (C4 (Web Text))

Max Activating Token Index: 837