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

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

Neuron 2615 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: 0.0957. Min Range: -0.0957

Max Act: 0.0957. Min Act: -0.0001

Data Index: 702733 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0919. Min Act: -0.0002

Data Index: 1071290 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0819. Min Act: -0.0002

Data Index: 509401 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0945. Min Act: -0.0002

Data Index: 745158 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0858. Min Act: -0.0002

Data Index: 29470 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0852. Min Act: -0.0001

Data Index: 184606 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0901. Min Act: -0.0002

Data Index: 873884 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0860. Min Act: -0.0002

Data Index: 179088 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0888. Min Act: -0.0002

Data Index: 361294 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0850. Min Act: -0.0002

Data Index: 93250 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0710. Min Act: -0.0002

Data Index: 388439 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0950. Min Act: -0.0002

Data Index: 608538 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0844. Min Act: -0.0001

Data Index: 333955 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0779. Min Act: -0.0001

Data Index: 1343991 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0827. Min Act: -0.0002

Data Index: 580473 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0788. Min Act: -0.0001

Data Index: 1041352 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0810. Min Act: -0.0002

Data Index: 519912 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0775. Min Act: -0.0002

Data Index: 352276 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0804. Min Act: -0.0002

Data Index: 1095110 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0795. Min Act: -0.0002

Data Index: 1050810 (C4 (Web Text))

Max Activating Token Index: 39