Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 635 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.6253. Min Act: -0.0000

Data Index: 886754 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.5758. Min Act: -0.0000

Data Index: 147534 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.5250. Min Act: -0.0000

Data Index: 1438 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.5970. Min Act: -0.0000

Data Index: 1150164 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1153143 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.5473. Min Act: -0.0000

Data Index: 581832 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.5438. Min Act: -0.0001

Data Index: 1008621 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.5493. Min Act: -0.0000

Data Index: 5426 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.6009. Min Act: -0.0000

Data Index: 1251917 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.5573. Min Act: -0.0000

Data Index: 1295490 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.5203. Min Act: -0.0001

Data Index: 764606 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.4877. Min Act: -0.0000

Data Index: 249331 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.5043. Min Act: -0.0000

Data Index: 473210 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.5239. Min Act: -0.0000

Data Index: 386447 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1164730 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.5096. Min Act: -0.0000

Data Index: 782097 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.4195. Min Act: -0.0000

Data Index: 784970 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.4784. Min Act: -0.0000

Data Index: 714083 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.4601. Min Act: -0.0000

Data Index: 234612 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.6253. Min Range: -0.6253

Max Act: 0.4583. Min Act: -0.0000

Data Index: 600104 (C4 (Web Text))

Max Activating Token Index: 125