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

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

Neuron 2346 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1233. Min Act: -0.0001

Data Index: 959865 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1183. Min Act: -0.0001

Data Index: 555871 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1111. Min Act: -0.0001

Data Index: 205381 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1094. Min Act: -0.0001

Data Index: 1289154 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1000. Min Act: -0.0001

Data Index: 681894 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0946. Min Act: -0.0001

Data Index: 750138 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1086. Min Act: -0.0001

Data Index: 861356 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0924. Min Act: -0.0001

Data Index: 711967 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0887. Min Act: -0.0001

Data Index: 845477 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0912. Min Act: -0.0001

Data Index: 273114 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0945. Min Act: -0.0001

Data Index: 918057 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0824. Min Act: -0.0001

Data Index: 598491 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0806. Min Act: -0.0001

Data Index: 1381 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0823. Min Act: -0.0001

Data Index: 1124086 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0877. Min Act: -0.0001

Data Index: 774354 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0809. Min Act: -0.0001

Data Index: 926586 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0837. Min Act: -0.0001

Data Index: 123612 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1200073 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0859. Min Act: -0.0001

Data Index: 654116 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0856. Min Act: -0.0001

Data Index: 878777 (C4 (Web Text))

Max Activating Token Index: 805