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

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

Neuron 4141 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5946. Min Range: -2.5946

Max Act: 2.5946. Min Act: -0.0000

Data Index: 1149667 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 2.5946. Min Range: -2.5946

Max Act: 2.5396. Min Act: -0.0000

Data Index: 582217 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 2.5946. Min Range: -2.5946

Max Act: 2.5638. Min Act: -0.0000

Data Index: 60114 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 2.5946. Min Range: -2.5946

Max Act: 2.5046. Min Act: -0.0000

Data Index: 486933 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 2.5946. Min Range: -2.5946

Max Act: 2.4909. Min Act: -0.0000

Data Index: 512088 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 2.5946. Min Range: -2.5946

Max Act: 2.4689. Min Act: -0.0000

Data Index: 189006 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 2.5946. Min Range: -2.5946

Max Act: 2.4746. Min Act: -0.0000

Data Index: 202380 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 2.5946. Min Range: -2.5946

Max Act: 2.4088. Min Act: -0.0000

Data Index: 1253233 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 2.5946. Min Range: -2.5946

Max Act: 2.2737. Min Act: -0.0000

Data Index: 714028 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 2.5946. Min Range: -2.5946

Max Act: 2.3801. Min Act: -0.0000

Data Index: 45895 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 2.5946. Min Range: -2.5946

Max Act: 2.2828. Min Act: -0.0000

Data Index: 177979 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 2.5946. Min Range: -2.5946

Max Act: 2.4857. Min Act: -0.0000

Data Index: 298590 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 2.5946. Min Range: -2.5946

Max Act: 2.3618. Min Act: -0.0000

Data Index: 657412 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 2.5946. Min Range: -2.5946

Max Act: 2.1906. Min Act: -0.0000

Data Index: 42120 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 2.5946. Min Range: -2.5946

Max Act: 2.2873. Min Act: -0.0000

Data Index: 963212 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 2.5946. Min Range: -2.5946

Max Act: 2.2845. Min Act: -0.0000

Data Index: 201359 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 2.5946. Min Range: -2.5946

Max Act: 2.2832. Min Act: -0.0000

Data Index: 145946 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 2.5946. Min Range: -2.5946

Max Act: 2.4018. Min Act: -0.0000

Data Index: 1635212 (Python Code)

Max Activating Token Index: 787

Text #18

Max Range: 2.5946. Min Range: -2.5946

Max Act: 2.2453. Min Act: -0.0000

Data Index: 833085 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 2.5946. Min Range: -2.5946

Max Act: 2.1449. Min Act: -0.0000

Data Index: 525250 (C4 (Web Text))

Max Activating Token Index: 581