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

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

Neuron 2781 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1591. Min Act: -0.0001

Data Index: 469467 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1640. Min Act: -0.0001

Data Index: 875169 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1586. Min Act: -0.0001

Data Index: 1050707 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1615. Min Act: -0.0001

Data Index: 619906 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1445. Min Act: -0.0001

Data Index: 45284 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1590. Min Act: -0.0001

Data Index: 693557 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1422. Min Act: -0.0001

Data Index: 1356341 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1411. Min Act: -0.0001

Data Index: 1289185 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1381. Min Act: -0.0001

Data Index: 283266 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1437. Min Act: -0.0001

Data Index: 1226841 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1251. Min Act: -0.0001

Data Index: 318801 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1216. Min Act: -0.0001

Data Index: 850335 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1218. Min Act: -0.0001

Data Index: 992398 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1308. Min Act: -0.0001

Data Index: 141807 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1258. Min Act: -0.0001

Data Index: 940884 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1056. Min Act: -0.0001

Data Index: 210192 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1200. Min Act: -0.0001

Data Index: 247177 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1270. Min Act: -0.0001

Data Index: 166231 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1126. Min Act: -0.0001

Data Index: 357822 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1161. Min Act: -0.0001

Data Index: 713528 (C4 (Web Text))

Max Activating Token Index: 722