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

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

Neuron 5062 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1721. Min Range: -1.1721

Max Act: 1.1721. Min Act: -0.0000

Data Index: 948200 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 1.1721. Min Range: -1.1721

Max Act: 1.1102. Min Act: -0.0000

Data Index: 480549 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 1.1721. Min Range: -1.1721

Max Act: 1.1171. Min Act: -0.0000

Data Index: 1126225 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.9721. Min Act: -0.0000

Data Index: 885925 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 1.1721. Min Range: -1.1721

Max Act: 1.0824. Min Act: -0.0000

Data Index: 633128 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 1.1721. Min Range: -1.1721

Max Act: 1.0237. Min Act: -0.0000

Data Index: 232654 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 1.1721. Min Range: -1.1721

Max Act: 1.0468. Min Act: -0.0000

Data Index: 1310825 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.9255. Min Act: -0.0000

Data Index: 135569 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1320183 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.8246. Min Act: -0.0000

Data Index: 679925 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.9117. Min Act: -0.0000

Data Index: 267542 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.8427. Min Act: -0.0000

Data Index: 253245 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.8618. Min Act: -0.0000

Data Index: 806566 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.8686. Min Act: -0.0000

Data Index: 318941 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.8175. Min Act: -0.0000

Data Index: 1050814 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.8660. Min Act: -0.0000

Data Index: 867290 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.8393. Min Act: -0.0000

Data Index: 828171 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.8384. Min Act: -0.0000

Data Index: 1181388 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.7986. Min Act: -0.0000

Data Index: 731637 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 1.1721. Min Range: -1.1721

Max Act: 0.8048. Min Act: -0.0000

Data Index: 1198024 (C4 (Web Text))

Max Activating Token Index: 554