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

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

Neuron 4433 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: 0.1553. Min Range: -0.1553

Max Act: 0.1553. Min Act: -0.0000

Data Index: 1105794 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0970. Min Act: -0.0000

Data Index: 45965 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1202. Min Act: -0.0000

Data Index: 832940 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1112. Min Act: -0.0000

Data Index: 1090835 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0910. Min Act: -0.0000

Data Index: 1566395 (Python Code)

Max Activating Token Index: 1018

Text #5

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1038. Min Act: -0.0000

Data Index: 296750 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0977. Min Act: -0.0000

Data Index: 392678 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0809. Min Act: -0.0000

Data Index: 1361653 (Python Code)

Max Activating Token Index: 985

Text #8

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1431423 (Python Code)

Max Activating Token Index: 963

Text #9

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0765. Min Act: -0.0000

Data Index: 1595979 (Python Code)

Max Activating Token Index: 965

Text #10

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0809. Min Act: -0.0000

Data Index: 787590 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0856. Min Act: -0.0000

Data Index: 81057 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0816. Min Act: -0.0000

Data Index: 240701 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0709. Min Act: -0.0000

Data Index: 1243851 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0776. Min Act: -0.0000

Data Index: 600767 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0802. Min Act: -0.0000

Data Index: 314411 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0827. Min Act: -0.0000

Data Index: 22855 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0808. Min Act: -0.0000

Data Index: 1341755 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0771. Min Act: -0.0000

Data Index: 28085 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0907. Min Act: -0.0000

Data Index: 367543 (C4 (Web Text))

Max Activating Token Index: 594