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

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

Neuron 744 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0943. Min Act: -0.0003

Data Index: 1288000 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0821. Min Act: -0.0003

Data Index: 1499284 (Python Code)

Max Activating Token Index: 695

Text #2

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0886. Min Act: -0.0003

Data Index: 683062 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0652. Min Act: -0.0003

Data Index: 663692 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0785. Min Act: -0.0003

Data Index: 483726 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0735. Min Act: -0.0003

Data Index: 79827 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0802. Min Act: -0.0003

Data Index: 282326 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0757. Min Act: -0.0003

Data Index: 789128 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0677. Min Act: -0.0003

Data Index: 79993 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0637. Min Act: -0.0003

Data Index: 534637 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0609. Min Act: -0.0003

Data Index: 980604 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0755. Min Act: -0.0003

Data Index: 1549864 (Python Code)

Max Activating Token Index: 12

Text #12

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0788. Min Act: -0.0003

Data Index: 800584 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0797. Min Act: -0.0003

Data Index: 888203 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0709. Min Act: -0.0003

Data Index: 139325 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0764. Min Act: -0.0003

Data Index: 417631 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0731. Min Act: -0.0003

Data Index: 1242632 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0730. Min Act: -0.0003

Data Index: 328181 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0724. Min Act: -0.0003

Data Index: 1039984 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0638. Min Act: -0.0003

Data Index: 1242673 (C4 (Web Text))

Max Activating Token Index: 760