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

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

Neuron 1564 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.8625. Min Act: -0.0001

Data Index: 1194278 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.6185. Min Act: -0.0001

Data Index: 309704 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.6323. Min Act: -0.0000

Data Index: 1217628 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.4902. Min Act: -0.0000

Data Index: 711887 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.4421. Min Act: -0.0000

Data Index: 448432 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.4081. Min Act: -0.0000

Data Index: 1359070 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.4171. Min Act: -0.0000

Data Index: 655773 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.4901. Min Act: -0.0000

Data Index: 324941 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.3621. Min Act: -0.0000

Data Index: 555286 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.3631. Min Act: -0.0000

Data Index: 1327133 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.4427. Min Act: -0.0000

Data Index: 766099 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.3621. Min Act: -0.0000

Data Index: 509033 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.3080. Min Act: -0.0000

Data Index: 230094 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.2547. Min Act: -0.0000

Data Index: 827378 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.3397. Min Act: -0.0000

Data Index: 1007748 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.2114. Min Act: -0.0000

Data Index: 323252 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.3251. Min Act: -0.0000

Data Index: 1248308 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.3129. Min Act: -0.0001

Data Index: 74214 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.2158. Min Act: -0.0000

Data Index: 920170 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.2953. Min Act: -0.0000

Data Index: 246285 (C4 (Web Text))

Max Activating Token Index: 97