Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2423 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1507. Min Act: -0.0000

Data Index: 203018 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1061. Min Act: -0.0001

Data Index: 762493 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1022. Min Act: -0.0000

Data Index: 389627 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0952. Min Act: -0.0000

Data Index: 691508 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1123662 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0927. Min Act: -0.0001

Data Index: 1021764 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0873. Min Act: -0.0000

Data Index: 1043144 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0869. Min Act: -0.0001

Data Index: 115326 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0837. Min Act: -0.0001

Data Index: 861867 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0815. Min Act: -0.0000

Data Index: 775073 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0811. Min Act: -0.0001

Data Index: 217689 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0837. Min Act: -0.0001

Data Index: 626182 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0817. Min Act: -0.0001

Data Index: 885098 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0813. Min Act: -0.0001

Data Index: 423212 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0808. Min Act: -0.0000

Data Index: 391423 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0800. Min Act: -0.0000

Data Index: 201991 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0803. Min Act: -0.0000

Data Index: 1095492 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0785. Min Act: -0.0000

Data Index: 484009 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0745. Min Act: -0.0000

Data Index: 273025 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0761. Min Act: -0.0001

Data Index: 603494 (C4 (Web Text))

Max Activating Token Index: 404