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

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

Neuron 2928 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: 2.3772. Min Range: -2.3772

Max Act: 2.3772. Min Act: -0.0000

Data Index: 855685 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 2.3772. Min Range: -2.3772

Max Act: 2.2747. Min Act: -0.0001

Data Index: 476787 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 2.3772. Min Range: -2.3772

Max Act: 2.2209. Min Act: -0.0001

Data Index: 136756 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 2.3772. Min Range: -2.3772

Max Act: 2.0545. Min Act: -0.0001

Data Index: 444550 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 2.3772. Min Range: -2.3772

Max Act: 1.9510. Min Act: -0.0000

Data Index: 985780 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 2.3772. Min Range: -2.3772

Max Act: 1.9216. Min Act: -0.0000

Data Index: 426362 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 2.3772. Min Range: -2.3772

Max Act: 1.8175. Min Act: -0.0000

Data Index: 1324534 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 2.3772. Min Range: -2.3772

Max Act: 1.9018. Min Act: -0.0000

Data Index: 546902 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 2.3772. Min Range: -2.3772

Max Act: 1.8006. Min Act: -0.0001

Data Index: 662356 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 2.3772. Min Range: -2.3772

Max Act: 1.6965. Min Act: -0.0000

Data Index: 1264684 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 2.3772. Min Range: -2.3772

Max Act: 1.6812. Min Act: -0.0000

Data Index: 426648 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 2.3772. Min Range: -2.3772

Max Act: 1.6457. Min Act: -0.0000

Data Index: 725334 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 2.3772. Min Range: -2.3772

Max Act: 1.6494. Min Act: -0.0000

Data Index: 1199742 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 2.3772. Min Range: -2.3772

Max Act: 1.6875. Min Act: -0.0001

Data Index: 210510 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 2.3772. Min Range: -2.3772

Max Act: 1.7206. Min Act: -0.0000

Data Index: 552670 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 2.3772. Min Range: -2.3772

Max Act: 1.6194. Min Act: -0.0001

Data Index: 906463 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 2.3772. Min Range: -2.3772

Max Act: 1.6155. Min Act: -0.0000

Data Index: 517306 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 2.3772. Min Range: -2.3772

Max Act: 1.6446. Min Act: -0.0000

Data Index: 702358 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 2.3772. Min Range: -2.3772

Max Act: 1.5218. Min Act: -0.0000

Data Index: 869687 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 2.3772. Min Range: -2.3772

Max Act: 1.6112. Min Act: -0.0000

Data Index: 1211698 (C4 (Web Text))

Max Activating Token Index: 841