Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 288 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1142. Min Act: -0.0003

Data Index: 616177 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1114. Min Act: -0.0003

Data Index: 1129560 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1072. Min Act: -0.0002

Data Index: 658529 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1038. Min Act: -0.0002

Data Index: 571628 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1025. Min Act: -0.0002

Data Index: 704415 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0978. Min Act: -0.0002

Data Index: 1053950 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0965. Min Act: -0.0003

Data Index: 1128139 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0928. Min Act: -0.0002

Data Index: 779551 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0931. Min Act: -0.0003

Data Index: 880855 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0917. Min Act: -0.0002

Data Index: 1170844 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0929. Min Act: -0.0002

Data Index: 240944 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0904. Min Act: -0.0002

Data Index: 460573 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0913. Min Act: -0.0003

Data Index: 835350 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0901. Min Act: -0.0003

Data Index: 158467 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0875. Min Act: -0.0002

Data Index: 96894 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0883. Min Act: -0.0003

Data Index: 568657 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0902. Min Act: -0.0003

Data Index: 749529 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0899. Min Act: -0.0002

Data Index: 1097488 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0871. Min Act: -0.0003

Data Index: 530183 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0886. Min Act: -0.0003

Data Index: 537506 (C4 (Web Text))

Max Activating Token Index: 11