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

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

Neuron 1900 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0076. Min Act: -0.0003

Data Index: 1280553 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0073. Min Act: -0.0003

Data Index: 274676 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0072. Min Act: -0.0004

Data Index: 129861 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0070. Min Act: -0.0003

Data Index: 801969 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0068. Min Act: -0.0003

Data Index: 854097 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0067. Min Act: -0.0003

Data Index: 603929 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0067. Min Act: -0.0003

Data Index: 358242 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0066. Min Act: -0.0003

Data Index: 65571 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0065. Min Act: -0.0004

Data Index: 786360 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0065. Min Act: -0.0004

Data Index: 1205419 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0064. Min Act: -0.0003

Data Index: 1141947 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0064. Min Act: -0.0003

Data Index: 952868 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0064. Min Act: -0.0004

Data Index: 911660 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0064. Min Act: -0.0003

Data Index: 727353 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0064. Min Act: -0.0003

Data Index: 1140439 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0064. Min Act: -0.0004

Data Index: 567001 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0063. Min Act: -0.0003

Data Index: 834537 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0063. Min Act: -0.0003

Data Index: 27235 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0063. Min Act: -0.0004

Data Index: 516599 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0063. Min Act: -0.0004

Data Index: 1199731 (C4 (Web Text))

Max Activating Token Index: 306