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

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

Neuron 1391 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: 0.4738. Min Range: -0.4738

Max Act: 0.4464. Min Act: -0.0001

Data Index: 361179 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.4738. Min Range: -0.4738

Max Act: 0.4279. Min Act: -0.0001

Data Index: 215865 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.4738. Min Range: -0.4738

Max Act: 0.4453. Min Act: -0.0001

Data Index: 376990 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.4738. Min Range: -0.4738

Max Act: 0.4738. Min Act: -0.0001

Data Index: 563871 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.4738. Min Range: -0.4738

Max Act: 0.4220. Min Act: -0.0001

Data Index: 1068013 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.4738. Min Range: -0.4738

Max Act: 0.3988. Min Act: -0.0000

Data Index: 250353 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 0.4738. Min Range: -0.4738

Max Act: 0.4132. Min Act: -0.0001

Data Index: 1032622 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 0.4738. Min Range: -0.4738

Max Act: 0.3486. Min Act: -0.0001

Data Index: 91700 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 0.4738. Min Range: -0.4738

Max Act: 0.4391. Min Act: -0.0001

Data Index: 913273 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.4738. Min Range: -0.4738

Max Act: 0.4363. Min Act: -0.0001

Data Index: 696728 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.4738. Min Range: -0.4738

Max Act: 0.3902. Min Act: -0.0001

Data Index: 580655 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.4738. Min Range: -0.4738

Max Act: 0.3550. Min Act: -0.0001

Data Index: 925616 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.4738. Min Range: -0.4738

Max Act: 0.3664. Min Act: -0.0001

Data Index: 1249656 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 0.4738. Min Range: -0.4738

Max Act: 0.3434. Min Act: -0.0001

Data Index: 51907 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 0.4738. Min Range: -0.4738

Max Act: 0.3917. Min Act: -0.0001

Data Index: 555528 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.4738. Min Range: -0.4738

Max Act: 0.3651. Min Act: -0.0001

Data Index: 217734 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.4738. Min Range: -0.4738

Max Act: 0.4252. Min Act: -0.0001

Data Index: 317367 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.4738. Min Range: -0.4738

Max Act: 0.4131. Min Act: -0.0001

Data Index: 1165529 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 0.4738. Min Range: -0.4738

Max Act: 0.3480. Min Act: -0.0001

Data Index: 1317330 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 0.4738. Min Range: -0.4738

Max Act: 0.4118. Min Act: -0.0001

Data Index: 946115 (C4 (Web Text))

Max Activating Token Index: 172