Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2902 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1553. Min Act: -0.0001

Data Index: 1356394 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1205. Min Act: -0.0001

Data Index: 847317 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0930. Min Act: -0.0001

Data Index: 1003967 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0622. Min Act: -0.0001

Data Index: 637169 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0822. Min Act: -0.0001

Data Index: 439630 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0818. Min Act: -0.0001

Data Index: 141992 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0811. Min Act: -0.0001

Data Index: 1106770 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0796. Min Act: -0.0001

Data Index: 711276 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0824. Min Act: -0.0001

Data Index: 74672 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0770. Min Act: -0.0001

Data Index: 1193938 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0787. Min Act: -0.0000

Data Index: 1337295 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0782. Min Act: -0.0000

Data Index: 552917 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0809. Min Act: -0.0001

Data Index: 514988 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0783. Min Act: -0.0001

Data Index: 835797 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0725. Min Act: -0.0001

Data Index: 339558 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0744. Min Act: -0.0001

Data Index: 61185 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0741. Min Act: 0.0005

Data Index: 779327 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0715. Min Act: -0.0001

Data Index: 888102 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0737. Min Act: -0.0001

Data Index: 1113996 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0741. Min Act: -0.0001

Data Index: 931903 (C4 (Web Text))

Max Activating Token Index: 719