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

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

Neuron 3408 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1082. Min Act: -0.0002

Data Index: 463914 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1046. Min Act: -0.0001

Data Index: 911856 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0974. Min Act: -0.0001

Data Index: 1329527 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0919. Min Act: -0.0001

Data Index: 780168 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0947. Min Act: -0.0002

Data Index: 846365 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0908. Min Act: -0.0001

Data Index: 60254 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0886. Min Act: -0.0002

Data Index: 357895 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0837. Min Act: -0.0002

Data Index: 29204 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0923. Min Act: -0.0002

Data Index: 1183136 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0912. Min Act: -0.0001

Data Index: 1275056 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0907. Min Act: -0.0002

Data Index: 1253191 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0879. Min Act: -0.0002

Data Index: 1299198 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0918. Min Act: -0.0002

Data Index: 139203 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0863. Min Act: -0.0002

Data Index: 1338173 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0865. Min Act: -0.0002

Data Index: 77053 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0887. Min Act: -0.0002

Data Index: 927349 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0794. Min Act: -0.0001

Data Index: 525209 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0848. Min Act: -0.0001

Data Index: 1196642 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0812. Min Act: -0.0001

Data Index: 141331 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0851. Min Act: -0.0002

Data Index: 1081891 (C4 (Web Text))

Max Activating Token Index: 4