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

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

Neuron 3028 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.7628. Min Act: -0.0000

Data Index: 119750 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.7352. Min Act: -0.0000

Data Index: 624587 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.7462. Min Act: -0.0000

Data Index: 257208 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.7383. Min Act: -0.0001

Data Index: 287884 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.7042. Min Act: -0.0000

Data Index: 763604 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6471. Min Act: -0.0000

Data Index: 403181 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6680. Min Act: -0.0000

Data Index: 779964 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6793. Min Act: -0.0001

Data Index: 326038 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6540. Min Act: 0.0000

Data Index: 880823 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6144. Min Act: -0.0000

Data Index: 174696 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6695. Min Act: -0.0001

Data Index: 226210 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6253. Min Act: 0.0000

Data Index: 210782 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6455. Min Act: -0.0000

Data Index: 1135322 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6184. Min Act: -0.0000

Data Index: 97422 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6230. Min Act: -0.0000

Data Index: 121546 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6443. Min Act: -0.0000

Data Index: 445772 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6159. Min Act: -0.0000

Data Index: 942008 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6187. Min Act: 0.0000

Data Index: 1258315 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.5719. Min Act: -0.0000

Data Index: 213271 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.5901. Min Act: 0.0000

Data Index: 984765 (C4 (Web Text))

Max Activating Token Index: 664