Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3642 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1703. Min Act: -0.0000

Data Index: 381371 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1487. Min Act: -0.0000

Data Index: 424140 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1465. Min Act: -0.0000

Data Index: 525695 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1323. Min Act: -0.0000

Data Index: 403084 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1288. Min Act: -0.0001

Data Index: 34671 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1534. Min Act: -0.0001

Data Index: 1268377 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1429. Min Act: -0.0000

Data Index: 391190 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1374. Min Act: -0.0000

Data Index: 912872 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1252. Min Act: -0.0000

Data Index: 673013 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1334. Min Act: -0.0000

Data Index: 492776 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1135. Min Act: -0.0001

Data Index: 804119 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1280. Min Act: -0.0001

Data Index: 1212794 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1108. Min Act: -0.0000

Data Index: 1064854 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1110. Min Act: -0.0000

Data Index: 25697 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.0975. Min Act: -0.0000

Data Index: 254636 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1111. Min Act: -0.0000

Data Index: 844852 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1031. Min Act: -0.0000

Data Index: 384326 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1034. Min Act: -0.0000

Data Index: 870200 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1039. Min Act: -0.0000

Data Index: 10290 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1338110 (C4 (Web Text))

Max Activating Token Index: 910