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

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

Neuron 1357 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0462. Min Range: -1.0462

Max Act: 1.0462. Min Act: -0.0001

Data Index: 931710 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.8118. Min Act: -0.0001

Data Index: 816666 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.7172. Min Act: -0.0001

Data Index: 734640 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.7402. Min Act: -0.0002

Data Index: 1044754 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.7189. Min Act: -0.0001

Data Index: 965963 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.6411. Min Act: -0.0001

Data Index: 419780 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.7283. Min Act: -0.0002

Data Index: 1191792 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.6324. Min Act: -0.0001

Data Index: 1154192 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.6939. Min Act: -0.0002

Data Index: 1244621 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.6995. Min Act: -0.0002

Data Index: 1267115 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.7081. Min Act: -0.0001

Data Index: 1195485 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.7295. Min Act: -0.0001

Data Index: 905517 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.6783. Min Act: -0.0002

Data Index: 816412 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.6825. Min Act: -0.0002

Data Index: 761608 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.6865. Min Act: -0.0001

Data Index: 70591 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.6159. Min Act: -0.0001

Data Index: 900359 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.7125. Min Act: -0.0001

Data Index: 740388 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.6684. Min Act: -0.0001

Data Index: 696874 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.6963. Min Act: -0.0001

Data Index: 213247 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 1.0462. Min Range: -1.0462

Max Act: 0.6459. Min Act: -0.0001

Data Index: 650326 (C4 (Web Text))

Max Activating Token Index: 121