Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1385 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1278. Min Act: -0.0001

Data Index: 838974 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1055. Min Act: -0.0001

Data Index: 632575 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0937. Min Act: -0.0001

Data Index: 764913 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0840. Min Act: -0.0001

Data Index: 1021553 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0818. Min Act: -0.0001

Data Index: 278231 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0768. Min Act: -0.0001

Data Index: 220898 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0782. Min Act: -0.0001

Data Index: 822359 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0767. Min Act: -0.0001

Data Index: 83266 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0751. Min Act: -0.0001

Data Index: 178691 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0770. Min Act: -0.0001

Data Index: 164481 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0695. Min Act: -0.0001

Data Index: 1092828 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0725. Min Act: -0.0001

Data Index: 35610 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0699. Min Act: -0.0001

Data Index: 778020 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0747. Min Act: -0.0001

Data Index: 1147108 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0694. Min Act: -0.0001

Data Index: 747204 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0741. Min Act: -0.0001

Data Index: 1214098 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0734. Min Act: -0.0001

Data Index: 6855 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0637. Min Act: -0.0001

Data Index: 443290 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0710. Min Act: -0.0001

Data Index: 1092707 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0703. Min Act: -0.0001

Data Index: 209355 (C4 (Web Text))

Max Activating Token Index: 727