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

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

Neuron 705 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5828. Min Range: -5.5828

Max Act: 5.4131. Min Act: -0.0001

Data Index: 911110 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 5.5828. Min Range: -5.5828

Max Act: 4.9128. Min Act: -0.0001

Data Index: 1103266 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 5.5828. Min Range: -5.5828

Max Act: 5.5828. Min Act: -0.0001

Data Index: 818834 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 5.5828. Min Range: -5.5828

Max Act: 5.2219. Min Act: -0.0001

Data Index: 595861 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 5.5828. Min Range: -5.5828

Max Act: 4.5652. Min Act: -0.0001

Data Index: 191813 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 5.5828. Min Range: -5.5828

Max Act: 5.0664. Min Act: -0.0001

Data Index: 419529 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 5.5828. Min Range: -5.5828

Max Act: 5.4017. Min Act: -0.0001

Data Index: 420635 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 5.5828. Min Range: -5.5828

Max Act: 4.7003. Min Act: -0.0001

Data Index: 289741 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 5.5828. Min Range: -5.5828

Max Act: 4.8378. Min Act: -0.0001

Data Index: 350398 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 5.5828. Min Range: -5.5828

Max Act: 5.3544. Min Act: -0.0001

Data Index: 677534 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 5.5828. Min Range: -5.5828

Max Act: 5.1380. Min Act: -0.0001

Data Index: 41246 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 5.5828. Min Range: -5.5828

Max Act: 4.8970. Min Act: -0.0001

Data Index: 371451 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 5.5828. Min Range: -5.5828

Max Act: 5.2230. Min Act: -0.0001

Data Index: 937831 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 5.5828. Min Range: -5.5828

Max Act: 4.6678. Min Act: -0.0001

Data Index: 774549 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 5.5828. Min Range: -5.5828

Max Act: 5.0416. Min Act: -0.0001

Data Index: 1270215 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 5.5828. Min Range: -5.5828

Max Act: 4.9959. Min Act: -0.0001

Data Index: 628192 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 5.5828. Min Range: -5.5828

Max Act: 4.0534. Min Act: -0.0001

Data Index: 199305 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 5.5828. Min Range: -5.5828

Max Act: 5.4658. Min Act: -0.0001

Data Index: 959309 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 5.5828. Min Range: -5.5828

Max Act: 4.3955. Min Act: -0.0001

Data Index: 754302 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 5.5828. Min Range: -5.5828

Max Act: 4.3399. Min Act: -0.0001

Data Index: 1229317 (C4 (Web Text))

Max Activating Token Index: 533