Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1641 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.8591. Min Act: -0.0000

Data Index: 1038501 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.7595. Min Act: -0.0000

Data Index: 1007655 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.5882. Min Act: -0.0000

Data Index: 770803 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.6191. Min Act: -0.0000

Data Index: 978610 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.4902. Min Act: -0.0000

Data Index: 1473004 (Python Code)

Max Activating Token Index: 272

Text #5

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.4978. Min Act: -0.0000

Data Index: 1269107 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.6767. Min Act: -0.0000

Data Index: 491308 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.6407. Min Act: -0.0000

Data Index: 122420 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.6139. Min Act: -0.0000

Data Index: 830683 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.6204. Min Act: -0.0000

Data Index: 930545 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.5436. Min Act: -0.0000

Data Index: 430902 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.4561. Min Act: -0.0000

Data Index: 1124919 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.4046. Min Act: -0.0000

Data Index: 187192 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.4117. Min Act: -0.0000

Data Index: 1002836 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.2726. Min Act: -0.0000

Data Index: 231049 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.2707. Min Act: -0.0000

Data Index: 1059642 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.2964. Min Act: -0.0000

Data Index: 612569 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.2020. Min Act: -0.0000

Data Index: 180449 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.2784. Min Act: -0.0000

Data Index: 288058 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.1481. Min Act: -0.0000

Data Index: 284742 (C4 (Web Text))

Max Activating Token Index: 718