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

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

Neuron 459 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: 0.0902. Min Range: -0.0902

Max Act: 0.0902. Min Act: -0.0002

Data Index: 362794 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0863. Min Act: -0.0002

Data Index: 1257857 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1234816 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1485568 (Python Code)

Max Activating Token Index: 604

Text #4

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0824. Min Act: -0.0002

Data Index: 339580 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0826. Min Act: -0.0002

Data Index: 802820 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1222047 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0795. Min Act: -0.0002

Data Index: 40586 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0805. Min Act: -0.0002

Data Index: 1564488 (Python Code)

Max Activating Token Index: 574

Text #9

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1219101 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0792. Min Act: -0.0002

Data Index: 646065 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0787. Min Act: -0.0002

Data Index: 201309 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0772. Min Act: -0.0002

Data Index: 764414 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0796. Min Act: -0.0002

Data Index: 682072 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0798. Min Act: -0.0002

Data Index: 594335 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1155017 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0764. Min Act: -0.0002

Data Index: 565589 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0756. Min Act: -0.0002

Data Index: 1281839 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0760. Min Act: -0.0002

Data Index: 277577 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0760. Min Act: -0.0002

Data Index: 599927 (C4 (Web Text))

Max Activating Token Index: 585