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

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

Neuron 2495 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1389. Min Act: -0.0001

Data Index: 962726 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1074. Min Act: -0.0001

Data Index: 1139836 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1214. Min Act: -0.0001

Data Index: 1104206 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1094. Min Act: -0.0001

Data Index: 288884 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1052. Min Act: -0.0001

Data Index: 1088412 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1069. Min Act: -0.0001

Data Index: 895365 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0894. Min Act: -0.0001

Data Index: 561577 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1032. Min Act: -0.0001

Data Index: 348636 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1011. Min Act: -0.0001

Data Index: 561112 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1078. Min Act: -0.0001

Data Index: 668826 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1092321 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0869. Min Act: -0.0001

Data Index: 1248610 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0981. Min Act: -0.0001

Data Index: 559282 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0858. Min Act: -0.0001

Data Index: 66692 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1020. Min Act: -0.0001

Data Index: 371176 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0922. Min Act: -0.0001

Data Index: 1004805 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0920. Min Act: -0.0001

Data Index: 986616 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0815. Min Act: -0.0001

Data Index: 1585002 (Python Code)

Max Activating Token Index: 795

Text #18

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0929. Min Act: -0.0001

Data Index: 120360 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0865. Min Act: -0.0001

Data Index: 1112246 (C4 (Web Text))

Max Activating Token Index: 238