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

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

Neuron 4438 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.1099. Min Act: -0.0002

Data Index: 459948 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.1074. Min Act: -0.0002

Data Index: 38888 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0968. Min Act: -0.0002

Data Index: 626068 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0933. Min Act: -0.0002

Data Index: 1058902 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0925. Min Act: -0.0002

Data Index: 630913 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0945. Min Act: -0.0002

Data Index: 1089790 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0950. Min Act: -0.0002

Data Index: 198720 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0851. Min Act: -0.0002

Data Index: 78550 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0905. Min Act: -0.0002

Data Index: 520910 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0894. Min Act: -0.0002

Data Index: 1273036 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0860. Min Act: -0.0002

Data Index: 536046 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0843. Min Act: -0.0002

Data Index: 32816 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0846. Min Act: -0.0002

Data Index: 953124 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0772. Min Act: -0.0002

Data Index: 601196 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0793. Min Act: -0.0002

Data Index: 1091268 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0770. Min Act: -0.0002

Data Index: 868939 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0745. Min Act: -0.0002

Data Index: 198874 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0720. Min Act: -0.0002

Data Index: 821583 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0727. Min Act: -0.0002

Data Index: 273223 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1175326 (C4 (Web Text))

Max Activating Token Index: 481