Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3056 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.9242. Min Act: -0.0001

Data Index: 296411 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.8823. Min Act: -0.0001

Data Index: 1097128 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.8005. Min Act: -0.0001

Data Index: 943878 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7255. Min Act: -0.0001

Data Index: 1128216 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7288. Min Act: -0.0001

Data Index: 1111015 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7486. Min Act: -0.0001

Data Index: 586955 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7006. Min Act: -0.0001

Data Index: 750610 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6753. Min Act: -0.0001

Data Index: 913900 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7127. Min Act: -0.0001

Data Index: 1295356 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6957. Min Act: -0.0001

Data Index: 339015 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6912. Min Act: -0.0001

Data Index: 1250697 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6771. Min Act: -0.0001

Data Index: 652909 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6994. Min Act: -0.0001

Data Index: 346270 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6310. Min Act: -0.0001

Data Index: 1148924 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6720. Min Act: -0.0001

Data Index: 1091532 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6899. Min Act: -0.0001

Data Index: 968808 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6315. Min Act: -0.0001

Data Index: 735788 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6511. Min Act: -0.0001

Data Index: 375015 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6262. Min Act: -0.0001

Data Index: 787145 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6297. Min Act: -0.0001

Data Index: 1124844 (C4 (Web Text))

Max Activating Token Index: 160