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

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

Neuron 1211 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5762. Min Act: -0.0000

Data Index: 206512 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5386. Min Act: 0.0000

Data Index: 912481 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5367. Min Act: -0.0000

Data Index: 1211852 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5161. Min Act: 0.0000

Data Index: 151146 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5116. Min Act: -0.0000

Data Index: 368111 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5004. Min Act: -0.0000

Data Index: 865339 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5011. Min Act: -0.0000

Data Index: 380364 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4848. Min Act: -0.0000

Data Index: 303137 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4911. Min Act: -0.0000

Data Index: 313561 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4504. Min Act: -0.0000

Data Index: 73264 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4362. Min Act: 0.0001

Data Index: 139491 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4305. Min Act: -0.0000

Data Index: 368409 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4154. Min Act: -0.0000

Data Index: 518377 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4134. Min Act: 0.0000

Data Index: 516857 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.3918. Min Act: 0.0000

Data Index: 140334 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.3882. Min Act: -0.0000

Data Index: 229250 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.3899. Min Act: -0.0000

Data Index: 201527 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.3909. Min Act: -0.0000

Data Index: 29214 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.3946. Min Act: -0.0000

Data Index: 941509 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.3951. Min Act: 0.0001

Data Index: 781298 (C4 (Web Text))

Max Activating Token Index: 929