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

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

Neuron 3711 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5769. Min Act: -0.0001

Data Index: 639495 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5589. Min Act: -0.0001

Data Index: 284996 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5759. Min Act: -0.0001

Data Index: 1186879 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5235. Min Act: -0.0001

Data Index: 837414 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5534. Min Act: -0.0001

Data Index: 726758 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5133. Min Act: -0.0001

Data Index: 1071131 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5552. Min Act: -0.0001

Data Index: 672122 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5309. Min Act: -0.0001

Data Index: 1224035 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4972. Min Act: -0.0001

Data Index: 958361 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5102. Min Act: -0.0001

Data Index: 1122162 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5074. Min Act: -0.0001

Data Index: 842829 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4903. Min Act: -0.0001

Data Index: 58037 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4643. Min Act: -0.0001

Data Index: 106596 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4746. Min Act: -0.0001

Data Index: 1178512 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4909. Min Act: -0.0001

Data Index: 413310 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4688. Min Act: -0.0001

Data Index: 1283263 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4823. Min Act: -0.0001

Data Index: 1312141 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4813. Min Act: -0.0001

Data Index: 44365 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4604. Min Act: -0.0001

Data Index: 1276398 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4771. Min Act: -0.0001

Data Index: 702653 (C4 (Web Text))

Max Activating Token Index: 603