Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1127 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0985. Min Act: -0.0002

Data Index: 1077165 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.1015. Min Act: -0.0002

Data Index: 592333 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.1026. Min Act: -0.0002

Data Index: 958101 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0952. Min Act: -0.0002

Data Index: 157278 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0919. Min Act: -0.0002

Data Index: 230101 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0890. Min Act: -0.0002

Data Index: 523949 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0914. Min Act: -0.0002

Data Index: 51511 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0868. Min Act: -0.0002

Data Index: 324728 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0923. Min Act: -0.0002

Data Index: 137316 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0844. Min Act: -0.0002

Data Index: 360107 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0738. Min Act: -0.0002

Data Index: 999232 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0901. Min Act: -0.0002

Data Index: 575818 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0833. Min Act: -0.0002

Data Index: 395175 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0887. Min Act: -0.0002

Data Index: 317105 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0911. Min Act: -0.0002

Data Index: 767787 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0937. Min Act: -0.0002

Data Index: 829383 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0899. Min Act: -0.0002

Data Index: 4405 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0899. Min Act: -0.0002

Data Index: 602356 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1082636 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0829. Min Act: -0.0002

Data Index: 57970 (C4 (Web Text))

Max Activating Token Index: 276