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

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

Neuron 1989 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0990. Min Act: -0.0000

Data Index: 528131 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0974. Min Act: -0.0000

Data Index: 795534 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0940. Min Act: -0.0000

Data Index: 104175 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0901. Min Act: -0.0000

Data Index: 1252573 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0936. Min Act: -0.0000

Data Index: 365320 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0862. Min Act: -0.0000

Data Index: 187315 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0890. Min Act: -0.0000

Data Index: 347495 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0822. Min Act: -0.0000

Data Index: 188132 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0784. Min Act: -0.0000

Data Index: 1208722 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0750. Min Act: -0.0000

Data Index: 1552260 (Python Code)

Max Activating Token Index: 370

Text #10

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0800. Min Act: -0.0000

Data Index: 9586 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0719. Min Act: -0.0000

Data Index: 452876 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0707. Min Act: -0.0000

Data Index: 740615 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0647. Min Act: -0.0000

Data Index: 1283354 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0714. Min Act: -0.0000

Data Index: 553957 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0675. Min Act: -0.0000

Data Index: 897922 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0703. Min Act: -0.0000

Data Index: 958856 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0628. Min Act: -0.0000

Data Index: 1005603 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0656. Min Act: -0.0000

Data Index: 209055 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0651. Min Act: -0.0000

Data Index: 1092289 (C4 (Web Text))

Max Activating Token Index: 67