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

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

Neuron 305 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: 0.9295. Min Range: -0.9295

Max Act: 0.9033. Min Act: -0.0001

Data Index: 501991 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.9295. Min Act: -0.0001

Data Index: 1015543 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.9005. Min Act: -0.0001

Data Index: 816959 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.8703. Min Act: -0.0001

Data Index: 144734 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.8007. Min Act: -0.0001

Data Index: 801588 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.8044. Min Act: -0.0001

Data Index: 918009 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7853. Min Act: -0.0001

Data Index: 309145 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6800. Min Act: -0.0001

Data Index: 1331320 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7084. Min Act: -0.0001

Data Index: 1060397 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6855. Min Act: -0.0001

Data Index: 703375 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7048. Min Act: -0.0001

Data Index: 65322 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6944. Min Act: -0.0001

Data Index: 1166703 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7180. Min Act: -0.0001

Data Index: 1194002 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6206. Min Act: -0.0001

Data Index: 152760 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.5943. Min Act: -0.0001

Data Index: 1101079 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6727. Min Act: -0.0001

Data Index: 1237491 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6067. Min Act: -0.0001

Data Index: 602538 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6419. Min Act: -0.0001

Data Index: 1058404 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6609. Min Act: -0.0001

Data Index: 555710 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6348. Min Act: -0.0001

Data Index: 798322 (C4 (Web Text))

Max Activating Token Index: 845