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

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

Neuron 1356 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: 0.1198. Min Range: -0.1198

Max Act: 0.1198. Min Act: -0.0001

Data Index: 215465 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1004. Min Act: -0.0001

Data Index: 334130 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1046. Min Act: -0.0001

Data Index: 655641 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0911. Min Act: -0.0001

Data Index: 251470 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0869. Min Act: -0.0001

Data Index: 556658 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0842. Min Act: -0.0001

Data Index: 178312 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0847. Min Act: -0.0001

Data Index: 16949 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1233476 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0723. Min Act: -0.0001

Data Index: 31126 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0725. Min Act: -0.0001

Data Index: 834146 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0785. Min Act: -0.0001

Data Index: 441389 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0699. Min Act: -0.0001

Data Index: 715926 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0684. Min Act: -0.0001

Data Index: 1309461 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0730. Min Act: -0.0001

Data Index: 328003 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0679. Min Act: -0.0001

Data Index: 881454 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0679. Min Act: -0.0001

Data Index: 485505 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0696. Min Act: -0.0001

Data Index: 516709 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0639. Min Act: -0.0001

Data Index: 487467 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0667. Min Act: -0.0001

Data Index: 1220823 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0710. Min Act: -0.0001

Data Index: 219365 (C4 (Web Text))

Max Activating Token Index: 594