Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1016 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1604. Min Act: -0.0001

Data Index: 800358 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1433. Min Act: -0.0001

Data Index: 436134 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1548. Min Act: -0.0001

Data Index: 533529 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1512. Min Act: -0.0001

Data Index: 392368 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1294. Min Act: -0.0001

Data Index: 1338674 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1133. Min Act: -0.0001

Data Index: 1286025 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1464. Min Act: -0.0001

Data Index: 58554 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1225. Min Act: -0.0001

Data Index: 1273658 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1515. Min Act: -0.0001

Data Index: 1093069 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1396. Min Act: -0.0001

Data Index: 118165 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1230. Min Act: -0.0001

Data Index: 112986 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1370. Min Act: -0.0001

Data Index: 64574 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1347. Min Act: -0.0001

Data Index: 1178712 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1252. Min Act: -0.0001

Data Index: 406889 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1300. Min Act: -0.0001

Data Index: 1126405 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1292. Min Act: -0.0001

Data Index: 670327 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1280. Min Act: -0.0001

Data Index: 244190 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1270. Min Act: -0.0001

Data Index: 895518 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1329. Min Act: -0.0001

Data Index: 920800 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1296. Min Act: -0.0001

Data Index: 520749 (C4 (Web Text))

Max Activating Token Index: 625