Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2687 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.6347. Min Act: -0.0001

Data Index: 739245 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4728. Min Act: -0.0001

Data Index: 450322 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4443. Min Act: -0.0001

Data Index: 1004908 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4593. Min Act: -0.0001

Data Index: 846357 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4251. Min Act: -0.0001

Data Index: 84900 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4274. Min Act: -0.0001

Data Index: 885078 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3937. Min Act: -0.0001

Data Index: 500492 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3887. Min Act: -0.0001

Data Index: 1126641 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4157. Min Act: -0.0001

Data Index: 1192308 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4251. Min Act: -0.0001

Data Index: 309422 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4486. Min Act: -0.0001

Data Index: 878111 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4052. Min Act: -0.0001

Data Index: 538499 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3748. Min Act: -0.0001

Data Index: 1256379 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4149. Min Act: -0.0001

Data Index: 739670 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3795. Min Act: -0.0001

Data Index: 1337192 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3637. Min Act: -0.0001

Data Index: 420393 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3770. Min Act: -0.0001

Data Index: 178041 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3733. Min Act: -0.0001

Data Index: 299782 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4084. Min Act: -0.0001

Data Index: 903139 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3946. Min Act: -0.0001

Data Index: 258196 (C4 (Web Text))

Max Activating Token Index: 441