Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2897 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9663. Min Range: -1.9663

Max Act: 1.8733. Min Act: -0.0001

Data Index: 707108 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 1.9663. Min Range: -1.9663

Max Act: 1.8420. Min Act: -0.0001

Data Index: 538816 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 1.9663. Min Range: -1.9663

Max Act: 1.9663. Min Act: -0.0001

Data Index: 1026878 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 1.9663. Min Range: -1.9663

Max Act: 1.7799. Min Act: -0.0001

Data Index: 316421 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 1.9663. Min Range: -1.9663

Max Act: 1.6536. Min Act: -0.0001

Data Index: 180931 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 1.9663. Min Range: -1.9663

Max Act: 1.5909. Min Act: -0.0001

Data Index: 1347225 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 1.9663. Min Range: -1.9663

Max Act: 1.2969. Min Act: -0.0001

Data Index: 918464 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 1.9663. Min Range: -1.9663

Max Act: 1.5536. Min Act: -0.0001

Data Index: 1057744 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 1.9663. Min Range: -1.9663

Max Act: 1.6128. Min Act: -0.0001

Data Index: 677454 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 1.9663. Min Range: -1.9663

Max Act: 1.6125. Min Act: -0.0001

Data Index: 220674 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 1.9663. Min Range: -1.9663

Max Act: 1.4241. Min Act: -0.0001

Data Index: 855221 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 1.9663. Min Range: -1.9663

Max Act: 1.1340. Min Act: -0.0001

Data Index: 120666 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 1.9663. Min Range: -1.9663

Max Act: 1.4304. Min Act: -0.0001

Data Index: 209300 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 1.9663. Min Range: -1.9663

Max Act: 1.4762. Min Act: -0.0001

Data Index: 1008596 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 1.9663. Min Range: -1.9663

Max Act: 1.3865. Min Act: -0.0001

Data Index: 58894 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 1.9663. Min Range: -1.9663

Max Act: 1.4808. Min Act: -0.0001

Data Index: 102555 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 1.9663. Min Range: -1.9663

Max Act: 1.3810. Min Act: -0.0001

Data Index: 228731 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 1.9663. Min Range: -1.9663

Max Act: 1.3041. Min Act: -0.0001

Data Index: 1162094 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 1.9663. Min Range: -1.9663

Max Act: 1.2584. Min Act: -0.0001

Data Index: 1304114 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 1.9663. Min Range: -1.9663

Max Act: 1.4552. Min Act: -0.0001

Data Index: 77847 (C4 (Web Text))

Max Activating Token Index: 1001