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

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

Neuron 3326 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: 0.3470. Min Range: -0.3470

Max Act: 0.3470. Min Act: -0.0001

Data Index: 49226 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.3167. Min Act: -0.0002

Data Index: 797018 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.3338. Min Act: -0.0001

Data Index: 1238922 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.3324. Min Act: -0.0002

Data Index: 789968 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.3099. Min Act: -0.0001

Data Index: 941477 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.3089. Min Act: -0.0002

Data Index: 17211 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2887. Min Act: -0.0001

Data Index: 297832 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.3015. Min Act: -0.0001

Data Index: 1033979 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2928. Min Act: -0.0002

Data Index: 992001 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2902. Min Act: -0.0001

Data Index: 152732 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.3011. Min Act: -0.0001

Data Index: 720138 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2883. Min Act: -0.0002

Data Index: 788224 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2735. Min Act: -0.0002

Data Index: 373015 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2870. Min Act: -0.0001

Data Index: 1057340 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2674. Min Act: -0.0001

Data Index: 6573 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2777. Min Act: -0.0002

Data Index: 1175094 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2773. Min Act: -0.0002

Data Index: 868320 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2754. Min Act: -0.0002

Data Index: 1331681 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2663. Min Act: -0.0001

Data Index: 815453 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.3470. Min Range: -0.3470

Max Act: 0.2477. Min Act: -0.0001

Data Index: 1024556 (C4 (Web Text))

Max Activating Token Index: 856