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

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

Neuron 2701 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1195. Min Act: -0.0003

Data Index: 552351 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1181. Min Act: -0.0003

Data Index: 16895 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1053. Min Act: -0.0003

Data Index: 275632 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0937. Min Act: -0.0003

Data Index: 915561 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0925. Min Act: -0.0003

Data Index: 840254 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1008. Min Act: -0.0003

Data Index: 1170205 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0971. Min Act: -0.0003

Data Index: 101070 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0904. Min Act: -0.0003

Data Index: 249712 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0930. Min Act: -0.0003

Data Index: 425893 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0939. Min Act: -0.0003

Data Index: 761467 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0923. Min Act: -0.0003

Data Index: 1234022 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0917. Min Act: -0.0003

Data Index: 161828 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0952. Min Act: -0.0003

Data Index: 1086050 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0847. Min Act: -0.0003

Data Index: 884982 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0950. Min Act: -0.0003

Data Index: 583889 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0871. Min Act: -0.0003

Data Index: 341082 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0903. Min Act: -0.0003

Data Index: 895945 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0898. Min Act: -0.0003

Data Index: 360127 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0837. Min Act: -0.0003

Data Index: 268603 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0891. Min Act: -0.0003

Data Index: 212810 (C4 (Web Text))

Max Activating Token Index: 501