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

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

Neuron 24 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: 0.4797. Min Range: -0.4797

Max Act: 0.4797. Min Act: -0.0001

Data Index: 221125 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.4551. Min Act: -0.0001

Data Index: 89423 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.4508. Min Act: -0.0001

Data Index: 495946 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.4453. Min Act: -0.0001

Data Index: 1053169 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.4600. Min Act: -0.0001

Data Index: 382625 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.4398. Min Act: -0.0001

Data Index: 731462 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.4313. Min Act: -0.0001

Data Index: 1256605 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.4282. Min Act: -0.0000

Data Index: 626098 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.4348. Min Act: -0.0001

Data Index: 21335 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.4049. Min Act: -0.0001

Data Index: 585170 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.3993. Min Act: -0.0001

Data Index: 31861 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.3873. Min Act: -0.0001

Data Index: 90477 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.3878. Min Act: -0.0001

Data Index: 139761 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.4188. Min Act: -0.0001

Data Index: 1102842 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.3914. Min Act: -0.0001

Data Index: 792543 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.4056. Min Act: -0.0001

Data Index: 1060640 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.4161. Min Act: -0.0001

Data Index: 1171748 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.3763. Min Act: -0.0001

Data Index: 760760 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.3742. Min Act: -0.0001

Data Index: 331099 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.4253. Min Act: -0.0001

Data Index: 1349294 (C4 (Web Text))

Max Activating Token Index: 802