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

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

Neuron 630 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.1246. Min Act: -0.0001

Data Index: 694283 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.1348. Min Act: -0.0001

Data Index: 748383 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.1228. Min Act: -0.0001

Data Index: 882093 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.1003. Min Act: -0.0001

Data Index: 602725 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.1034. Min Act: -0.0001

Data Index: 58079 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.1184. Min Act: -0.0001

Data Index: 635259 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0987. Min Act: -0.0001

Data Index: 426249 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0709. Min Act: -0.0001

Data Index: 302258 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0916. Min Act: -0.0001

Data Index: 359057 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.1078. Min Act: -0.0001

Data Index: 798680 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0944. Min Act: -0.0001

Data Index: 203805 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0694. Min Act: -0.0001

Data Index: 1339702 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.1029. Min Act: -0.0001

Data Index: 568540 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0930. Min Act: -0.0001

Data Index: 774261 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0991. Min Act: -0.0001

Data Index: 360500 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0917. Min Act: -0.0001

Data Index: 83170 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.1006. Min Act: -0.0001

Data Index: 1029937 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0933. Min Act: -0.0001

Data Index: 819263 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0712. Min Act: -0.0001

Data Index: 1154035 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0934. Min Act: -0.0001

Data Index: 796315 (C4 (Web Text))

Max Activating Token Index: 49