Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2645 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4674. Min Range: -2.4674

Max Act: 2.4674. Min Act: -0.0000

Data Index: 1198849 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 2.4674. Min Range: -2.4674

Max Act: 2.1770. Min Act: -0.0000

Data Index: 69142 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 2.4674. Min Range: -2.4674

Max Act: 2.1181. Min Act: -0.0000

Data Index: 1293256 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 2.4674. Min Range: -2.4674

Max Act: 2.1321. Min Act: -0.0000

Data Index: 402031 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 2.4674. Min Range: -2.4674

Max Act: 2.1117. Min Act: -0.0000

Data Index: 920828 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 2.4674. Min Range: -2.4674

Max Act: 1.7648. Min Act: -0.0000

Data Index: 832897 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 2.4674. Min Range: -2.4674

Max Act: 1.9996. Min Act: -0.0000

Data Index: 224877 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 2.4674. Min Range: -2.4674

Max Act: 2.0660. Min Act: -0.0000

Data Index: 576983 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 2.4674. Min Range: -2.4674

Max Act: 2.0384. Min Act: -0.0000

Data Index: 380375 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 2.4674. Min Range: -2.4674

Max Act: 2.1600. Min Act: -0.0000

Data Index: 1047130 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 2.4674. Min Range: -2.4674

Max Act: 1.9950. Min Act: -0.0000

Data Index: 195546 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 2.4674. Min Range: -2.4674

Max Act: 2.0580. Min Act: -0.0000

Data Index: 800852 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 2.4674. Min Range: -2.4674

Max Act: 1.9827. Min Act: -0.0000

Data Index: 828276 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 2.4674. Min Range: -2.4674

Max Act: 2.0750. Min Act: -0.0000

Data Index: 1348417 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 2.4674. Min Range: -2.4674

Max Act: 2.0159. Min Act: -0.0000

Data Index: 486312 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 2.4674. Min Range: -2.4674

Max Act: 2.0037. Min Act: -0.0000

Data Index: 1237833 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 2.4674. Min Range: -2.4674

Max Act: 2.0036. Min Act: -0.0000

Data Index: 861657 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 2.4674. Min Range: -2.4674

Max Act: 2.0927. Min Act: -0.0000

Data Index: 996729 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 2.4674. Min Range: -2.4674

Max Act: 2.1380. Min Act: -0.0000

Data Index: 338861 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 2.4674. Min Range: -2.4674

Max Act: 1.9676. Min Act: -0.0000

Data Index: 365868 (C4 (Web Text))

Max Activating Token Index: 730