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

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

Neuron 265 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.4984. Min Act: -0.0000

Data Index: 1098880 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.5023. Min Act: -0.0000

Data Index: 410417 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.4586. Min Act: -0.0000

Data Index: 274091 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1200345 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1255105 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.4278. Min Act: -0.0000

Data Index: 1045267 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1316529 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.4362. Min Act: -0.0000

Data Index: 40545 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.4160. Min Act: -0.0000

Data Index: 951532 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.4115. Min Act: -0.0000

Data Index: 313466 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.4208. Min Act: -0.0000

Data Index: 433876 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.3781. Min Act: -0.0000

Data Index: 560657 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.4017. Min Act: -0.0000

Data Index: 106458 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.3987. Min Act: -0.0000

Data Index: 8684 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.3950. Min Act: -0.0000

Data Index: 333 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.3834. Min Act: -0.0000

Data Index: 519608 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.3931. Min Act: -0.0000

Data Index: 964517 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.3791. Min Act: -0.0000

Data Index: 753495 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.3900. Min Act: -0.0000

Data Index: 969790 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.5023. Min Range: -0.5023

Max Act: 0.3903. Min Act: -0.0000

Data Index: 779115 (C4 (Web Text))

Max Activating Token Index: 492