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

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

Neuron 650 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: 1.7591. Min Range: -1.7591

Max Act: 1.7591. Min Act: -0.0001

Data Index: 154195 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.7469. Min Act: -0.0000

Data Index: 697721 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.6837. Min Act: -0.0000

Data Index: 246525 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.6874. Min Act: -0.0000

Data Index: 150052 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.4887. Min Act: -0.0000

Data Index: 669564 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.5430. Min Act: -0.0000

Data Index: 544341 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.5652. Min Act: -0.0000

Data Index: 523786 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.4951. Min Act: -0.0001

Data Index: 1167330 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.4139. Min Act: -0.0000

Data Index: 1234898 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.4181. Min Act: -0.0000

Data Index: 1141173 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.3667. Min Act: -0.0001

Data Index: 1108448 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.3489. Min Act: -0.0000

Data Index: 920073 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.4327. Min Act: -0.0000

Data Index: 44332 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.3539. Min Act: -0.0000

Data Index: 154373 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.3747. Min Act: -0.0000

Data Index: 749221 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.3684. Min Act: -0.0000

Data Index: 1347764 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.3224. Min Act: -0.0001

Data Index: 822500 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.2822. Min Act: -0.0001

Data Index: 1345328 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.3029. Min Act: -0.0000

Data Index: 101884 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.3058. Min Act: -0.0000

Data Index: 553520 (C4 (Web Text))

Max Activating Token Index: 523