Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 276 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1416. Min Act: -0.0002

Data Index: 496569 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1235. Min Act: -0.0001

Data Index: 396270 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1212. Min Act: -0.0002

Data Index: 505122 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1126. Min Act: -0.0001

Data Index: 354694 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1046. Min Act: -0.0001

Data Index: 679 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1049. Min Act: -0.0002

Data Index: 661270 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1093. Min Act: -0.0002

Data Index: 572858 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1052. Min Act: -0.0002

Data Index: 1296852 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1025. Min Act: -0.0002

Data Index: 890522 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1023. Min Act: -0.0002

Data Index: 712565 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0960. Min Act: -0.0002

Data Index: 333530 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0957. Min Act: -0.0002

Data Index: 1227266 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0942. Min Act: -0.0002

Data Index: 860731 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0930. Min Act: -0.0002

Data Index: 348788 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0942. Min Act: -0.0002

Data Index: 834601 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1197558 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0938. Min Act: -0.0002

Data Index: 66104 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0980. Min Act: -0.0002

Data Index: 136948 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0933. Min Act: -0.0002

Data Index: 390879 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0935. Min Act: -0.0002

Data Index: 717367 (C4 (Web Text))

Max Activating Token Index: 540