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

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

Neuron 1172 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: 0.9833. Min Range: -0.9833

Max Act: 0.8942. Min Act: -0.0001

Data Index: 952699 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.9833. Min Act: -0.0000

Data Index: 863544 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.9339. Min Act: -0.0000

Data Index: 581700 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.8750. Min Act: -0.0001

Data Index: 811487 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.8510. Min Act: -0.0001

Data Index: 1206669 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.8192. Min Act: -0.0001

Data Index: 242281 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.8480. Min Act: -0.0000

Data Index: 780840 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.8389. Min Act: -0.0001

Data Index: 844187 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.8698. Min Act: -0.0001

Data Index: 572517 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.8480. Min Act: -0.0000

Data Index: 1159405 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.8227. Min Act: -0.0001

Data Index: 167646 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.8701. Min Act: -0.0001

Data Index: 790428 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.8064. Min Act: -0.0000

Data Index: 1055879 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.7792. Min Act: -0.0000

Data Index: 1291087 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.7689. Min Act: -0.0001

Data Index: 857014 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.8164. Min Act: -0.0001

Data Index: 1038677 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.7383. Min Act: -0.0001

Data Index: 887413 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.7804. Min Act: -0.0001

Data Index: 987668 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.7167. Min Act: -0.0001

Data Index: 783598 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 0.9833. Min Range: -0.9833

Max Act: 0.7105. Min Act: -0.0001

Data Index: 1353633 (C4 (Web Text))

Max Activating Token Index: 567