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

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

Neuron 4690 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.0824. Min Range: -1.0824

Max Act: 1.0788. Min Act: -0.0002

Data Index: 1131893 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 1.0824. Min Range: -1.0824

Max Act: 1.0780. Min Act: -0.0002

Data Index: 1080853 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 1.0824. Min Range: -1.0824

Max Act: 1.0824. Min Act: -0.0002

Data Index: 392882 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 1.0824. Min Range: -1.0824

Max Act: 1.0136. Min Act: -0.0002

Data Index: 48702 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 1.0824. Min Range: -1.0824

Max Act: 1.0224. Min Act: -0.0002

Data Index: 677740 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 1.0824. Min Range: -1.0824

Max Act: 1.0380. Min Act: -0.0002

Data Index: 327778 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 1.0824. Min Range: -1.0824

Max Act: 1.0329. Min Act: -0.0002

Data Index: 569590 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 1.0824. Min Range: -1.0824

Max Act: 1.0243. Min Act: -0.0002

Data Index: 15385 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 1.0824. Min Range: -1.0824

Max Act: 1.0019. Min Act: -0.0002

Data Index: 1192750 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9978. Min Act: -0.0002

Data Index: 166853 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9720. Min Act: -0.0002

Data Index: 1060286 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 1.0824. Min Range: -1.0824

Max Act: 1.0055. Min Act: -0.0002

Data Index: 385532 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9851. Min Act: -0.0002

Data Index: 533224 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9831. Min Act: -0.0002

Data Index: 1273917 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9834. Min Act: -0.0002

Data Index: 1358089 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9624. Min Act: -0.0002

Data Index: 193270 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9660. Min Act: -0.0002

Data Index: 925433 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9848. Min Act: -0.0002

Data Index: 8453 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9584. Min Act: -0.0002

Data Index: 707268 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 1.0824. Min Range: -1.0824

Max Act: 0.9438. Min Act: -0.0002

Data Index: 521350 (C4 (Web Text))

Max Activating Token Index: 733