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

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

Neuron 1620 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: 0.3940. Min Range: -0.3940

Max Act: 0.3649. Min Act: -0.0001

Data Index: 737073 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 0.3940. Min Range: -0.3940

Max Act: 0.3940. Min Act: -0.0000

Data Index: 991614 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.3940. Min Range: -0.3940

Max Act: 0.3362. Min Act: -0.0000

Data Index: 905622 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 0.3940. Min Range: -0.3940

Max Act: 0.3456. Min Act: -0.0001

Data Index: 969906 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.3940. Min Range: -0.3940

Max Act: 0.3236. Min Act: -0.0001

Data Index: 248475 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.3940. Min Range: -0.3940

Max Act: 0.2851. Min Act: -0.0001

Data Index: 1354119 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.3940. Min Range: -0.3940

Max Act: 0.3056. Min Act: -0.0001

Data Index: 96572 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.3940. Min Range: -0.3940

Max Act: 0.2994. Min Act: -0.0001

Data Index: 824334 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.3940. Min Range: -0.3940

Max Act: 0.2714. Min Act: -0.0001

Data Index: 1208976 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.3940. Min Range: -0.3940

Max Act: 0.3100. Min Act: -0.0000

Data Index: 1320021 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.3940. Min Range: -0.3940

Max Act: 0.2981. Min Act: -0.0000

Data Index: 1030662 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 0.3940. Min Range: -0.3940

Max Act: 0.2933. Min Act: -0.0001

Data Index: 777203 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 0.3940. Min Range: -0.3940

Max Act: 0.2827. Min Act: -0.0001

Data Index: 1102392 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.3940. Min Range: -0.3940

Max Act: 0.3013. Min Act: -0.0001

Data Index: 499158 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.3940. Min Range: -0.3940

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1047229 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 0.3940. Min Range: -0.3940

Max Act: 0.2836. Min Act: -0.0000

Data Index: 1105761 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.3940. Min Range: -0.3940

Max Act: 0.2950. Min Act: -0.0000

Data Index: 923240 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.3940. Min Range: -0.3940

Max Act: 0.2903. Min Act: -0.0000

Data Index: 395984 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.3940. Min Range: -0.3940

Max Act: 0.2910. Min Act: -0.0001

Data Index: 685754 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 0.3940. Min Range: -0.3940

Max Act: 0.2824. Min Act: -0.0000

Data Index: 1308869 (C4 (Web Text))

Max Activating Token Index: 726