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

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

Neuron 3165 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0899. Min Act: -0.0001

Data Index: 715157 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1127173 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0877. Min Act: -0.0001

Data Index: 257969 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0873. Min Act: -0.0001

Data Index: 992936 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0845. Min Act: -0.0001

Data Index: 633967 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0822. Min Act: -0.0001

Data Index: 1221545 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0820. Min Act: -0.0001

Data Index: 208014 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0798. Min Act: -0.0001

Data Index: 412723 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0794. Min Act: -0.0001

Data Index: 356984 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0796. Min Act: -0.0001

Data Index: 1165530 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0816. Min Act: -0.0001

Data Index: 875624 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0787. Min Act: -0.0001

Data Index: 177259 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0782. Min Act: -0.0001

Data Index: 1244188 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0772. Min Act: -0.0001

Data Index: 290061 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0772. Min Act: -0.0001

Data Index: 307252 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0745. Min Act: -0.0001

Data Index: 431765 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0770. Min Act: -0.0001

Data Index: 1021977 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0762. Min Act: -0.0001

Data Index: 977701 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0768. Min Act: -0.0001

Data Index: 67465 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0790. Min Act: -0.0001

Data Index: 558074 (C4 (Web Text))

Max Activating Token Index: 96