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

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

Neuron 3308 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: 0.1046. Min Range: -0.1046

Max Act: 0.1007. Min Act: -0.0002

Data Index: 644085 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.1046. Min Act: -0.0002

Data Index: 1140424 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0979. Min Act: -0.0002

Data Index: 708172 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0861. Min Act: -0.0002

Data Index: 643887 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0916. Min Act: -0.0002

Data Index: 1037632 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0967. Min Act: -0.0002

Data Index: 562616 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0964. Min Act: -0.0002

Data Index: 666055 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0940. Min Act: -0.0002

Data Index: 636977 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0935. Min Act: -0.0002

Data Index: 726679 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0886. Min Act: -0.0002

Data Index: 932417 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0904. Min Act: -0.0002

Data Index: 1259379 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0897. Min Act: -0.0002

Data Index: 558600 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0880. Min Act: -0.0002

Data Index: 743738 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0644. Min Act: -0.0002

Data Index: 15931 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0852. Min Act: -0.0002

Data Index: 559138 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0911. Min Act: -0.0002

Data Index: 813279 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0851. Min Act: -0.0002

Data Index: 752568 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0871. Min Act: -0.0002

Data Index: 244354 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0867. Min Act: -0.0002

Data Index: 1186961 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0854. Min Act: -0.0002

Data Index: 1426268 (Python Code)

Max Activating Token Index: 11