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

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

Neuron 5552 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: 0.1234. Min Range: -0.1234

Max Act: 0.1077. Min Act: -0.0001

Data Index: 653110 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1234. Min Act: -0.0001

Data Index: 142329 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1027. Min Act: -0.0001

Data Index: 61862 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0893. Min Act: -0.0001

Data Index: 641094 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1089728 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1148. Min Act: -0.0001

Data Index: 699613 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0978. Min Act: -0.0001

Data Index: 29643 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0959. Min Act: -0.0001

Data Index: 331033 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0850. Min Act: -0.0001

Data Index: 244441 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0923. Min Act: -0.0001

Data Index: 192333 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0928. Min Act: -0.0001

Data Index: 1283754 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0915. Min Act: -0.0001

Data Index: 54513 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0848. Min Act: -0.0001

Data Index: 1103198 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0914. Min Act: -0.0001

Data Index: 1111131 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0861. Min Act: -0.0001

Data Index: 787861 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0741. Min Act: -0.0001

Data Index: 363815 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0732. Min Act: -0.0001

Data Index: 447567 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0818. Min Act: -0.0001

Data Index: 444713 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0797. Min Act: -0.0001

Data Index: 1280714 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0964. Min Act: -0.0001

Data Index: 1063691 (C4 (Web Text))

Max Activating Token Index: 192