Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4720 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1352. Min Act: -0.0001

Data Index: 494494 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1091. Min Act: -0.0000

Data Index: 181555 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0951. Min Act: -0.0001

Data Index: 304810 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1019. Min Act: -0.0000

Data Index: 570084 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0949. Min Act: -0.0000

Data Index: 635590 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0932. Min Act: -0.0000

Data Index: 898566 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0931. Min Act: -0.0000

Data Index: 666265 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0923. Min Act: -0.0000

Data Index: 150798 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0887. Min Act: -0.0000

Data Index: 812306 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0908. Min Act: -0.0000

Data Index: 1085337 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0942. Min Act: -0.0000

Data Index: 1080883 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0899. Min Act: -0.0000

Data Index: 809281 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0861. Min Act: -0.0000

Data Index: 779952 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0874. Min Act: -0.0000

Data Index: 402703 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0909. Min Act: -0.0000

Data Index: 801633 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0868. Min Act: -0.0000

Data Index: 719310 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0863. Min Act: -0.0000

Data Index: 125262 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0838. Min Act: -0.0001

Data Index: 305963 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0855. Min Act: -0.0000

Data Index: 258525 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0785. Min Act: -0.0000

Data Index: 1179476 (C4 (Web Text))

Max Activating Token Index: 163