Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3218 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0835. Min Act: -0.0001

Data Index: 677893 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0861. Min Act: -0.0001

Data Index: 712368 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0810. Min Act: -0.0001

Data Index: 998761 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0886. Min Act: -0.0001

Data Index: 1181078 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0837. Min Act: -0.0001

Data Index: 470824 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0811. Min Act: -0.0001

Data Index: 293571 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0676. Min Act: -0.0001

Data Index: 969670 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0759. Min Act: -0.0001

Data Index: 699346 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0782. Min Act: -0.0001

Data Index: 621346 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0796. Min Act: -0.0001

Data Index: 216544 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0762. Min Act: -0.0001

Data Index: 867353 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0685. Min Act: -0.0001

Data Index: 978883 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0733. Min Act: -0.0001

Data Index: 17274 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0807. Min Act: -0.0001

Data Index: 1235338 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0680. Min Act: -0.0001

Data Index: 604558 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0699. Min Act: -0.0001

Data Index: 820487 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0726. Min Act: -0.0001

Data Index: 134876 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0693. Min Act: -0.0001

Data Index: 989185 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0706. Min Act: -0.0001

Data Index: 828389 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0657. Min Act: -0.0001

Data Index: 279093 (C4 (Web Text))

Max Activating Token Index: 368