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

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

Neuron 4458 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4026. Min Range: -0.4026

Max Act: 0.3704. Min Act: -0.0001

Data Index: 731629 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.4026. Min Range: -0.4026

Max Act: 0.3671. Min Act: -0.0001

Data Index: 113072 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 0.4026. Min Range: -0.4026

Max Act: 0.4026. Min Act: -0.0001

Data Index: 625464 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.4026. Min Range: -0.4026

Max Act: 0.3877. Min Act: -0.0001

Data Index: 520900 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.4026. Min Range: -0.4026

Max Act: 0.3145. Min Act: -0.0001

Data Index: 1135375 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.4026. Min Range: -0.4026

Max Act: 0.3077. Min Act: -0.0001

Data Index: 372923 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.4026. Min Range: -0.4026

Max Act: 0.3292. Min Act: -0.0001

Data Index: 237297 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.4026. Min Range: -0.4026

Max Act: 0.3146. Min Act: -0.0001

Data Index: 145292 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.4026. Min Range: -0.4026

Max Act: 0.3117. Min Act: -0.0001

Data Index: 1049066 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 0.4026. Min Range: -0.4026

Max Act: 0.3206. Min Act: -0.0001

Data Index: 5083 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 0.4026. Min Range: -0.4026

Max Act: 0.3178. Min Act: -0.0001

Data Index: 993263 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.4026. Min Range: -0.4026

Max Act: 0.2853. Min Act: -0.0001

Data Index: 956916 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 0.4026. Min Range: -0.4026

Max Act: 0.2950. Min Act: -0.0001

Data Index: 852655 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 0.4026. Min Range: -0.4026

Max Act: 0.3033. Min Act: -0.0001

Data Index: 1004760 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.4026. Min Range: -0.4026

Max Act: 0.2990. Min Act: -0.0001

Data Index: 586054 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.4026. Min Range: -0.4026

Max Act: 0.2746. Min Act: -0.0001

Data Index: 742172 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.4026. Min Range: -0.4026

Max Act: 0.2780. Min Act: -0.0001

Data Index: 1339113 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 0.4026. Min Range: -0.4026

Max Act: 0.2859. Min Act: -0.0001

Data Index: 569533 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.4026. Min Range: -0.4026

Max Act: 0.2925. Min Act: -0.0001

Data Index: 1320013 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.4026. Min Range: -0.4026

Max Act: 0.2855. Min Act: -0.0001

Data Index: 685492 (C4 (Web Text))

Max Activating Token Index: 727