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

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

Neuron 2488 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7222. Min Range: -2.7222

Max Act: 2.7222. Min Act: -0.0000

Data Index: 676464 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 2.7222. Min Range: -2.7222

Max Act: 2.3473. Min Act: -0.0000

Data Index: 366 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 2.7222. Min Range: -2.7222

Max Act: 2.2981. Min Act: -0.0000

Data Index: 633035 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 2.7222. Min Range: -2.7222

Max Act: 2.2899. Min Act: -0.0000

Data Index: 866619 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 2.7222. Min Range: -2.7222

Max Act: 2.2643. Min Act: -0.0000

Data Index: 249940 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 2.7222. Min Range: -2.7222

Max Act: 2.0213. Min Act: -0.0000

Data Index: 909502 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 2.7222. Min Range: -2.7222

Max Act: 2.0138. Min Act: -0.0000

Data Index: 978267 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 2.7222. Min Range: -2.7222

Max Act: 2.0143. Min Act: -0.0000

Data Index: 1232106 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 2.7222. Min Range: -2.7222

Max Act: 2.0110. Min Act: -0.0000

Data Index: 1014112 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 2.7222. Min Range: -2.7222

Max Act: 2.0020. Min Act: -0.0000

Data Index: 966039 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 2.7222. Min Range: -2.7222

Max Act: 2.0107. Min Act: -0.0000

Data Index: 1159165 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 2.7222. Min Range: -2.7222

Max Act: 1.8745. Min Act: -0.0000

Data Index: 953286 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 2.7222. Min Range: -2.7222

Max Act: 1.9588. Min Act: -0.0000

Data Index: 677704 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 2.7222. Min Range: -2.7222

Max Act: 1.8664. Min Act: -0.0000

Data Index: 780193 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 2.7222. Min Range: -2.7222

Max Act: 1.9601. Min Act: -0.0000

Data Index: 100118 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 2.7222. Min Range: -2.7222

Max Act: 1.8596. Min Act: -0.0000

Data Index: 629011 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 2.7222. Min Range: -2.7222

Max Act: 1.9372. Min Act: -0.0000

Data Index: 1029760 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 2.7222. Min Range: -2.7222

Max Act: 1.9422. Min Act: -0.0000

Data Index: 64426 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 2.7222. Min Range: -2.7222

Max Act: 1.9487. Min Act: -0.0000

Data Index: 585454 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 2.7222. Min Range: -2.7222

Max Act: 1.9245. Min Act: -0.0000

Data Index: 1215954 (C4 (Web Text))

Max Activating Token Index: 187