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

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

Neuron 1376 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3714. Min Range: -1.3714

Max Act: 1.3714. Min Act: -0.0001

Data Index: 331959 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 1.3714. Min Range: -1.3714

Max Act: 1.2666. Min Act: -0.0001

Data Index: 645235 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 1.3714. Min Range: -1.3714

Max Act: 1.2149. Min Act: -0.0001

Data Index: 1227396 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 1.3714. Min Range: -1.3714

Max Act: 1.1217. Min Act: -0.0001

Data Index: 1239962 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 1.3714. Min Range: -1.3714

Max Act: 1.0886. Min Act: -0.0001

Data Index: 1217166 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 1.3714. Min Range: -1.3714

Max Act: 1.0648. Min Act: -0.0001

Data Index: 294662 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.9862. Min Act: -0.0001

Data Index: 358397 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.9223. Min Act: -0.0001

Data Index: 629893 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 1.3714. Min Range: -1.3714

Max Act: 1.0387. Min Act: -0.0001

Data Index: 901719 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.9118. Min Act: -0.0001

Data Index: 116749 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.9517. Min Act: -0.0001

Data Index: 109001 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.9265. Min Act: -0.0001

Data Index: 756674 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.8692. Min Act: -0.0001

Data Index: 443929 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.8034. Min Act: -0.0001

Data Index: 1054822 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.8884. Min Act: -0.0001

Data Index: 1095324 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.8662. Min Act: -0.0001

Data Index: 673246 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.8765. Min Act: -0.0001

Data Index: 237161 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.9043. Min Act: -0.0001

Data Index: 1354183 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.8671. Min Act: -0.0001

Data Index: 1250844 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 1.3714. Min Range: -1.3714

Max Act: 0.9882. Min Act: -0.0001

Data Index: 112502 (C4 (Web Text))

Max Activating Token Index: 519