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

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

Neuron 4606 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2864. Min Range: -0.2864

Max Act: 0.2864. Min Act: -0.0000

Data Index: 664545 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 0.2864. Min Range: -0.2864

Max Act: 0.2607. Min Act: -0.0000

Data Index: 911512 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.2864. Min Range: -0.2864

Max Act: 0.2358. Min Act: -0.0000

Data Index: 487793 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.2864. Min Range: -0.2864

Max Act: 0.2258. Min Act: -0.0000

Data Index: 593222 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.2864. Min Range: -0.2864

Max Act: 0.2149. Min Act: -0.0000

Data Index: 920293 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.2864. Min Range: -0.2864

Max Act: 0.2093. Min Act: -0.0000

Data Index: 1060818 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.2864. Min Range: -0.2864

Max Act: 0.2154. Min Act: -0.0000

Data Index: 4539 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.2864. Min Range: -0.2864

Max Act: 0.2123. Min Act: -0.0000

Data Index: 1198301 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.2864. Min Range: -0.2864

Max Act: 0.1856. Min Act: -0.0000

Data Index: 1238433 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.2864. Min Range: -0.2864

Max Act: 0.2021. Min Act: 0.0000

Data Index: 1297075 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.2864. Min Range: -0.2864

Max Act: 0.1884. Min Act: -0.0000

Data Index: 276218 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 0.2864. Min Range: -0.2864

Max Act: 0.1761. Min Act: 0.0000

Data Index: 1265863 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.2864. Min Range: -0.2864

Max Act: 0.1490. Min Act: -0.0000

Data Index: 611274 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.2864. Min Range: -0.2864

Max Act: 0.1660. Min Act: -0.0000

Data Index: 468735 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.2864. Min Range: -0.2864

Max Act: 0.1617. Min Act: 0.0000

Data Index: 806337 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 0.2864. Min Range: -0.2864

Max Act: 0.1653. Min Act: -0.0000

Data Index: 972017 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 0.2864. Min Range: -0.2864

Max Act: 0.1529. Min Act: -0.0000

Data Index: 595226 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.2864. Min Range: -0.2864

Max Act: 0.1647. Min Act: -0.0000

Data Index: 672175 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 0.2864. Min Range: -0.2864

Max Act: 0.1470. Min Act: -0.0000

Data Index: 488266 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.2864. Min Range: -0.2864

Max Act: 0.1672. Min Act: -0.0000

Data Index: 425019 (C4 (Web Text))

Max Activating Token Index: 908