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

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

Neuron 4607 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: 1.0909. Min Range: -1.0909

Max Act: 1.0821. Min Act: -0.0002

Data Index: 83453 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 1.0909. Min Range: -1.0909

Max Act: 1.0909. Min Act: -0.0002

Data Index: 469879 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 1.0909. Min Range: -1.0909

Max Act: 1.0507. Min Act: -0.0002

Data Index: 1510809 (Python Code)

Max Activating Token Index: 933

Text #3

Max Range: 1.0909. Min Range: -1.0909

Max Act: 1.0636. Min Act: -0.0002

Data Index: 970338 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 1.0909. Min Range: -1.0909

Max Act: 1.0724. Min Act: -0.0002

Data Index: 220618 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 1.0909. Min Range: -1.0909

Max Act: 1.0300. Min Act: -0.0002

Data Index: 995879 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 1.0909. Min Range: -1.0909

Max Act: 1.0402. Min Act: -0.0002

Data Index: 62066 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 1.0909. Min Range: -1.0909

Max Act: 1.0259. Min Act: -0.0002

Data Index: 1130257 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 1.0909. Min Range: -1.0909

Max Act: 1.0136. Min Act: -0.0002

Data Index: 913709 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 1.0909. Min Range: -1.0909

Max Act: 1.0208. Min Act: -0.0002

Data Index: 685054 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 1.0909. Min Range: -1.0909

Max Act: 1.0334. Min Act: -0.0002

Data Index: 760058 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.9987. Min Act: -0.0002

Data Index: 388231 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.9907. Min Act: -0.0002

Data Index: 348701 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 1.0909. Min Range: -1.0909

Max Act: 1.0183. Min Act: -0.0002

Data Index: 1140084 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 1.0909. Min Range: -1.0909

Max Act: 1.0242. Min Act: -0.0002

Data Index: 1084239 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.9797. Min Act: -0.0002

Data Index: 236756 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 1.0909. Min Range: -1.0909

Max Act: 1.0085. Min Act: -0.0002

Data Index: 155436 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.9961. Min Act: -0.0002

Data Index: 735179 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.9633. Min Act: -0.0002

Data Index: 1057424 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 1.0909. Min Range: -1.0909

Max Act: 0.9678. Min Act: -0.0002

Data Index: 926805 (C4 (Web Text))

Max Activating Token Index: 64