Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5045 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0903. Min Act: -0.0002

Data Index: 792885 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0859. Min Act: -0.0002

Data Index: 262468 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0862. Min Act: -0.0002

Data Index: 935497 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0887. Min Act: -0.0002

Data Index: 907427 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0874. Min Act: -0.0002

Data Index: 28207 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0848. Min Act: -0.0002

Data Index: 261280 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1070477 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0834. Min Act: -0.0002

Data Index: 439243 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0856. Min Act: -0.0002

Data Index: 385423 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0845. Min Act: -0.0002

Data Index: 296453 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0849. Min Act: -0.0002

Data Index: 770345 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0832. Min Act: -0.0002

Data Index: 1195297 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0839. Min Act: -0.0002

Data Index: 409384 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0833. Min Act: -0.0002

Data Index: 1163691 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1075965 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0814. Min Act: -0.0002

Data Index: 315125 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0825. Min Act: -0.0002

Data Index: 482066 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1275442 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0817. Min Act: -0.0002

Data Index: 50598 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0799. Min Act: -0.0002

Data Index: 594028 (C4 (Web Text))

Max Activating Token Index: 316