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

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

Neuron 3233 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.4687. Min Act: -0.0001

Data Index: 694589 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.4413. Min Act: -0.0001

Data Index: 659038 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1260767 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3256. Min Act: -0.0000

Data Index: 424873 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3248. Min Act: -0.0001

Data Index: 1085561 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1012043 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3071. Min Act: -0.0001

Data Index: 313997 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3008. Min Act: -0.0000

Data Index: 319686 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.2992. Min Act: -0.0000

Data Index: 744264 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1234148 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.2814. Min Act: -0.0001

Data Index: 11247 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.2689. Min Act: -0.0001

Data Index: 433147 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.2827. Min Act: -0.0000

Data Index: 573296 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.2742. Min Act: -0.0000

Data Index: 1081474 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.2717. Min Act: -0.0000

Data Index: 902594 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.2612. Min Act: -0.0000

Data Index: 516360 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.2701. Min Act: -0.0000

Data Index: 898348 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.2611. Min Act: -0.0001

Data Index: 1185817 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.2561. Min Act: -0.0001

Data Index: 762271 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.2549. Min Act: -0.0000

Data Index: 1252974 (C4 (Web Text))

Max Activating Token Index: 375