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

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

Neuron 2098 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2852. Min Range: -1.2852

Max Act: 1.2799. Min Act: -0.0001

Data Index: 665908 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 1.2852. Min Range: -1.2852

Max Act: 1.2852. Min Act: -0.0001

Data Index: 1085768 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 1.2852. Min Range: -1.2852

Max Act: 1.2504. Min Act: -0.0001

Data Index: 735353 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 1.2852. Min Range: -1.2852

Max Act: 1.1584. Min Act: -0.0001

Data Index: 997325 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 1.2852. Min Range: -1.2852

Max Act: 1.0486. Min Act: -0.0001

Data Index: 1141857 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 1.2852. Min Range: -1.2852

Max Act: 1.0216. Min Act: -0.0001

Data Index: 1270380 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 1.2852. Min Range: -1.2852

Max Act: 1.0785. Min Act: -0.0001

Data Index: 1309989 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 1.2852. Min Range: -1.2852

Max Act: 0.9412. Min Act: -0.0001

Data Index: 1075768 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 1.2852. Min Range: -1.2852

Max Act: 1.0607. Min Act: -0.0001

Data Index: 1267064 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 1.2852. Min Range: -1.2852

Max Act: 1.0203. Min Act: -0.0001

Data Index: 510959 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 1.2852. Min Range: -1.2852

Max Act: 0.9653. Min Act: -0.0001

Data Index: 823211 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 1.2852. Min Range: -1.2852

Max Act: 0.9648. Min Act: -0.0001

Data Index: 1321101 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 1.2852. Min Range: -1.2852

Max Act: 0.9881. Min Act: -0.0001

Data Index: 494178 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 1.2852. Min Range: -1.2852

Max Act: 0.9692. Min Act: -0.0001

Data Index: 852615 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 1.2852. Min Range: -1.2852

Max Act: 0.9474. Min Act: -0.0001

Data Index: 1192957 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 1.2852. Min Range: -1.2852

Max Act: 0.8327. Min Act: -0.0001

Data Index: 596118 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 1.2852. Min Range: -1.2852

Max Act: 0.9793. Min Act: -0.0001

Data Index: 729229 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 1.2852. Min Range: -1.2852

Max Act: 0.9433. Min Act: -0.0001

Data Index: 25220 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 1.2852. Min Range: -1.2852

Max Act: 0.9099. Min Act: 0.0000

Data Index: 1059979 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 1.2852. Min Range: -1.2852

Max Act: 0.9692. Min Act: -0.0001

Data Index: 243308 (C4 (Web Text))

Max Activating Token Index: 508