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

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

Neuron 2970 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.3147. Min Act: -0.0000

Data Index: 1077132 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.2616. Min Act: -0.0000

Data Index: 1249717 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.2438. Min Act: -0.0000

Data Index: 591380 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.2254. Min Act: -0.0000

Data Index: 679207 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0889. Min Act: -0.0000

Data Index: 1314915 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0649. Min Act: -0.0000

Data Index: 985047 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0874. Min Act: -0.0000

Data Index: 392967 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.1110. Min Act: -0.0000

Data Index: 747157 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.1086. Min Act: -0.0000

Data Index: 1326756 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0825. Min Act: -0.0000

Data Index: 734268 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0782. Min Act: -0.0000

Data Index: 615014 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.1061. Min Act: -0.0000

Data Index: 51345 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0649. Min Act: -0.0000

Data Index: 897153 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0510. Min Act: -0.0000

Data Index: 162446 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0217. Min Act: -0.0000

Data Index: 880078 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0391. Min Act: -0.0000

Data Index: 1044844 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0095. Min Act: -0.0000

Data Index: 1214003 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0061. Min Act: -0.0000

Data Index: 1199284 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0086. Min Act: -0.0000

Data Index: 501565 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 1.3147. Min Range: -1.3147

Max Act: 1.0051. Min Act: -0.0000

Data Index: 529372 (C4 (Web Text))

Max Activating Token Index: 498