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

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

Neuron 3904 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4200. Min Range: -3.4200

Max Act: 3.4200. Min Act: -0.0000

Data Index: 593656 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.7044. Min Act: -0.0000

Data Index: 8120 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.4853. Min Act: -0.0000

Data Index: 1294138 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.4144. Min Act: -0.0000

Data Index: 336384 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.1401. Min Act: -0.0000

Data Index: 1059162 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.1024. Min Act: -0.0000

Data Index: 496386 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.1106. Min Act: -0.0000

Data Index: 1147310 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 3.4200. Min Range: -3.4200

Max Act: 1.8501. Min Act: -0.0000

Data Index: 996916 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 3.4200. Min Range: -3.4200

Max Act: 1.7420. Min Act: -0.0000

Data Index: 358600 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 3.4200. Min Range: -3.4200

Max Act: 1.8297. Min Act: -0.0000

Data Index: 228070 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 3.4200. Min Range: -3.4200

Max Act: 1.9012. Min Act: -0.0000

Data Index: 964147 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 3.4200. Min Range: -3.4200

Max Act: 1.8259. Min Act: -0.0000

Data Index: 22814 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 3.4200. Min Range: -3.4200

Max Act: 1.5877. Min Act: -0.0000

Data Index: 111611 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 3.4200. Min Range: -3.4200

Max Act: 1.5129. Min Act: -0.0000

Data Index: 1152973 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 3.4200. Min Range: -3.4200

Max Act: 1.5617. Min Act: -0.0000

Data Index: 1133884 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 3.4200. Min Range: -3.4200

Max Act: 1.5640. Min Act: -0.0000

Data Index: 299852 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 3.4200. Min Range: -3.4200

Max Act: 1.6466. Min Act: -0.0000

Data Index: 966030 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 3.4200. Min Range: -3.4200

Max Act: 1.4406. Min Act: -0.0000

Data Index: 780837 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 3.4200. Min Range: -3.4200

Max Act: 1.5173. Min Act: -0.0000

Data Index: 1307013 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 3.4200. Min Range: -3.4200

Max Act: 1.5016. Min Act: -0.0000

Data Index: 1164382 (C4 (Web Text))

Max Activating Token Index: 332