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

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

Neuron 939 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: 4.3548. Min Range: -4.3548

Max Act: 3.7568. Min Act: -0.0001

Data Index: 1098444 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 4.3548. Min Range: -4.3548

Max Act: 3.6689. Min Act: -0.0001

Data Index: 668038 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 4.3548. Min Range: -4.3548

Max Act: 4.3548. Min Act: -0.0001

Data Index: 925324 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 4.3548. Min Range: -4.3548

Max Act: 3.6762. Min Act: -0.0000

Data Index: 106406 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 4.3548. Min Range: -4.3548

Max Act: 3.7524. Min Act: -0.0001

Data Index: 793826 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 4.3548. Min Range: -4.3548

Max Act: 3.2706. Min Act: -0.0001

Data Index: 298810 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 4.3548. Min Range: -4.3548

Max Act: 3.4906. Min Act: -0.0001

Data Index: 1154399 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 4.3548. Min Range: -4.3548

Max Act: 3.5101. Min Act: -0.0001

Data Index: 213019 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 4.3548. Min Range: -4.3548

Max Act: 3.3419. Min Act: -0.0000

Data Index: 609877 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 4.3548. Min Range: -4.3548

Max Act: 3.1604. Min Act: -0.0001

Data Index: 832298 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 4.3548. Min Range: -4.3548

Max Act: 3.2309. Min Act: -0.0001

Data Index: 1154218 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 4.3548. Min Range: -4.3548

Max Act: 3.2242. Min Act: -0.0001

Data Index: 1007154 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 4.3548. Min Range: -4.3548

Max Act: 3.2183. Min Act: -0.0000

Data Index: 1023937 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 4.3548. Min Range: -4.3548

Max Act: 3.1597. Min Act: -0.0001

Data Index: 512034 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 4.3548. Min Range: -4.3548

Max Act: 2.9983. Min Act: -0.0001

Data Index: 195637 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 4.3548. Min Range: -4.3548

Max Act: 3.2720. Min Act: -0.0001

Data Index: 11635 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 4.3548. Min Range: -4.3548

Max Act: 3.0603. Min Act: -0.0001

Data Index: 129481 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 4.3548. Min Range: -4.3548

Max Act: 3.0746. Min Act: -0.0001

Data Index: 234801 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 4.3548. Min Range: -4.3548

Max Act: 3.1478. Min Act: -0.0001

Data Index: 616523 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 4.3548. Min Range: -4.3548

Max Act: 3.1915. Min Act: -0.0001

Data Index: 483761 (C4 (Web Text))

Max Activating Token Index: 163