Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 951 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0885. Min Act: -0.0003

Data Index: 1070224 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0884. Min Act: -0.0003

Data Index: 1021301 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0890. Min Act: -0.0003

Data Index: 271464 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0909. Min Act: -0.0003

Data Index: 1337312 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0935. Min Act: -0.0003

Data Index: 117447 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0886. Min Act: -0.0003

Data Index: 1235595 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0877. Min Act: -0.0003

Data Index: 1197563 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0839. Min Act: -0.0003

Data Index: 586686 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0878. Min Act: -0.0003

Data Index: 477878 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0836. Min Act: -0.0003

Data Index: 305312 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0858. Min Act: -0.0003

Data Index: 1123324 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0790. Min Act: -0.0003

Data Index: 1054275 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0806. Min Act: -0.0003

Data Index: 125935 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0822. Min Act: -0.0003

Data Index: 2008 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0844. Min Act: -0.0003

Data Index: 231268 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0793. Min Act: -0.0003

Data Index: 775646 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0806. Min Act: -0.0003

Data Index: 632230 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0796. Min Act: -0.0003

Data Index: 1010800 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0831. Min Act: -0.0003

Data Index: 520490 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0751. Min Act: -0.0003

Data Index: 476773 (C4 (Web Text))

Max Activating Token Index: 48