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

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

Neuron 2107 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: 1.2054. Min Range: -1.2054

Max Act: 1.2054. Min Act: -0.0000

Data Index: 626697 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 1.2054. Min Range: -1.2054

Max Act: 1.1778. Min Act: -0.0000

Data Index: 1165679 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 1.2054. Min Range: -1.2054

Max Act: 1.1492. Min Act: -0.0000

Data Index: 523983 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 1.2054. Min Range: -1.2054

Max Act: 1.0679. Min Act: -0.0000

Data Index: 868728 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 1.2054. Min Range: -1.2054

Max Act: 1.0008. Min Act: -0.0000

Data Index: 208049 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.9911. Min Act: -0.0000

Data Index: 728790 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 1.2054. Min Range: -1.2054

Max Act: 1.0131. Min Act: -0.0000

Data Index: 701370 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.9661. Min Act: -0.0000

Data Index: 388950 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.9219. Min Act: -0.0000

Data Index: 791716 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 1.2054. Min Range: -1.2054

Max Act: 1.0032. Min Act: -0.0000

Data Index: 10315 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.9441. Min Act: -0.0000

Data Index: 550673 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.9014. Min Act: -0.0000

Data Index: 1225430 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.9654. Min Act: -0.0000

Data Index: 391909 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.9210. Min Act: -0.0000

Data Index: 180426 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.8413. Min Act: -0.0000

Data Index: 260233 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.8078. Min Act: -0.0000

Data Index: 1059654 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.8691. Min Act: -0.0000

Data Index: 346351 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.8474. Min Act: -0.0000

Data Index: 1078706 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.8060. Min Act: -0.0000

Data Index: 227522 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 1.2054. Min Range: -1.2054

Max Act: 0.8015. Min Act: -0.0000

Data Index: 575278 (C4 (Web Text))

Max Activating Token Index: 103