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

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

Neuron 1573 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1740. Min Act: -0.0001

Data Index: 376581 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1604. Min Act: -0.0001

Data Index: 211709 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1630. Min Act: -0.0001

Data Index: 909026 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1501. Min Act: -0.0001

Data Index: 838522 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1578. Min Act: -0.0001

Data Index: 992105 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1533. Min Act: -0.0001

Data Index: 657197 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1509. Min Act: -0.0001

Data Index: 176092 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1406. Min Act: -0.0001

Data Index: 491495 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1476. Min Act: -0.0001

Data Index: 754445 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1332. Min Act: -0.0001

Data Index: 212216 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1407. Min Act: -0.0001

Data Index: 298113 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1317. Min Act: -0.0001

Data Index: 644627 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1399. Min Act: -0.0001

Data Index: 986290 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1285. Min Act: -0.0001

Data Index: 585989 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1342. Min Act: -0.0001

Data Index: 956882 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1331. Min Act: -0.0001

Data Index: 414615 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1292. Min Act: -0.0001

Data Index: 411457 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1162. Min Act: -0.0001

Data Index: 1273134 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1316. Min Act: -0.0001

Data Index: 319816 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1265. Min Act: -0.0001

Data Index: 699870 (C4 (Web Text))

Max Activating Token Index: 773