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

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

Neuron 102 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.3347. Min Act: -0.0001

Data Index: 349368 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.3224. Min Act: -0.0001

Data Index: 236549 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.3051. Min Act: -0.0001

Data Index: 140556 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.3363. Min Act: -0.0001

Data Index: 158062 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2738. Min Act: -0.0001

Data Index: 540087 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2975. Min Act: -0.0001

Data Index: 101614 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.3006. Min Act: -0.0001

Data Index: 1292136 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2964. Min Act: -0.0001

Data Index: 740980 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2781. Min Act: -0.0001

Data Index: 896447 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2733. Min Act: -0.0001

Data Index: 226207 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2624. Min Act: -0.0001

Data Index: 394978 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2723. Min Act: -0.0001

Data Index: 1275046 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2699. Min Act: -0.0001

Data Index: 769010 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2719. Min Act: -0.0001

Data Index: 1073279 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2773. Min Act: -0.0001

Data Index: 301420 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2768. Min Act: -0.0001

Data Index: 578851 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2729. Min Act: -0.0001

Data Index: 1139897 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.3057. Min Act: -0.0001

Data Index: 1190142 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2605. Min Act: -0.0001

Data Index: 987562 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.3363. Min Range: -0.3363

Max Act: 0.2680. Min Act: -0.0001

Data Index: 487604 (C4 (Web Text))

Max Activating Token Index: 673