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

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

Neuron 3800 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: 0.1072. Min Range: -0.1072

Max Act: 0.1072. Min Act: -0.0000

Data Index: 6987 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0906. Min Act: -0.0000

Data Index: 466750 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0945. Min Act: -0.0000

Data Index: 1060387 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0906. Min Act: -0.0000

Data Index: 146073 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0912. Min Act: -0.0000

Data Index: 167955 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0879. Min Act: -0.0000

Data Index: 297257 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0838. Min Act: -0.0000

Data Index: 599160 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0864. Min Act: -0.0000

Data Index: 757696 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0834. Min Act: -0.0000

Data Index: 304488 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0858. Min Act: -0.0000

Data Index: 319399 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0809. Min Act: -0.0000

Data Index: 1147382 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0888. Min Act: -0.0000

Data Index: 875351 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0832. Min Act: -0.0000

Data Index: 499867 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0805. Min Act: -0.0000

Data Index: 642050 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0760. Min Act: -0.0000

Data Index: 254827 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0771. Min Act: -0.0001

Data Index: 545182 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0783. Min Act: -0.0000

Data Index: 873427 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0770. Min Act: -0.0000

Data Index: 587509 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0774. Min Act: -0.0000

Data Index: 786552 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0779. Min Act: -0.0000

Data Index: 175810 (C4 (Web Text))

Max Activating Token Index: 780