Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2741 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.2590. Min Act: -0.0001

Data Index: 480591 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.2764. Min Act: -0.0001

Data Index: 340811 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 3.2764. Min Range: -3.2764

Max Act: 3.1825. Min Act: -0.0001

Data Index: 719159 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.7926. Min Act: -0.0002

Data Index: 903484 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.8295. Min Act: -0.0002

Data Index: 402668 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.5562. Min Act: -0.0001

Data Index: 1049152 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.5469. Min Act: -0.0001

Data Index: 409547 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.7961. Min Act: -0.0001

Data Index: 449149 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.5751. Min Act: -0.0001

Data Index: 95099 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.0173. Min Act: -0.0002

Data Index: 1016475 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.4806. Min Act: -0.0001

Data Index: 368131 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.4205. Min Act: -0.0002

Data Index: 1062721 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.4083. Min Act: -0.0002

Data Index: 616307 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.2894. Min Act: -0.0002

Data Index: 406026 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.3774. Min Act: -0.0002

Data Index: 442855 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.4523. Min Act: -0.0002

Data Index: 241641 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.3238. Min Act: -0.0001

Data Index: 1112486 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.3730. Min Act: -0.0002

Data Index: 270317 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.3764. Min Act: -0.0002

Data Index: 956397 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 3.2764. Min Range: -3.2764

Max Act: 2.4755. Min Act: -0.0001

Data Index: 230842 (C4 (Web Text))

Max Activating Token Index: 356