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

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

Neuron 15 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: 0.4682. Min Range: -0.4682

Max Act: 0.4289. Min Act: -0.0000

Data Index: 382143 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 0.4682. Min Range: -0.4682

Max Act: 0.4682. Min Act: -0.0000

Data Index: 406865 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.4682. Min Range: -0.4682

Max Act: 0.4564. Min Act: -0.0000

Data Index: 124846 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.4682. Min Range: -0.4682

Max Act: 0.4410. Min Act: -0.0000

Data Index: 1229078 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.4682. Min Range: -0.4682

Max Act: 0.4571. Min Act: -0.0000

Data Index: 1041209 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 0.4682. Min Range: -0.4682

Max Act: 0.4542. Min Act: -0.0000

Data Index: 49829 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.4682. Min Range: -0.4682

Max Act: 0.4518. Min Act: -0.0000

Data Index: 457831 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 0.4682. Min Range: -0.4682

Max Act: 0.4478. Min Act: -0.0000

Data Index: 48030 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 0.4682. Min Range: -0.4682

Max Act: 0.4224. Min Act: -0.0000

Data Index: 210418 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.4682. Min Range: -0.4682

Max Act: 0.4049. Min Act: -0.0000

Data Index: 402107 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.4682. Min Range: -0.4682

Max Act: 0.4319. Min Act: -0.0000

Data Index: 192957 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.4682. Min Range: -0.4682

Max Act: 0.4308. Min Act: -0.0000

Data Index: 810875 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 0.4682. Min Range: -0.4682

Max Act: 0.4216. Min Act: -0.0000

Data Index: 333682 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 0.4682. Min Range: -0.4682

Max Act: 0.3889. Min Act: -0.0000

Data Index: 1168806 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 0.4682. Min Range: -0.4682

Max Act: 0.3972. Min Act: -0.0000

Data Index: 87569 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.4682. Min Range: -0.4682

Max Act: 0.4329. Min Act: -0.0000

Data Index: 1110717 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 0.4682. Min Range: -0.4682

Max Act: 0.4317. Min Act: -0.0000

Data Index: 77910 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.4682. Min Range: -0.4682

Max Act: 0.4222. Min Act: -0.0000

Data Index: 990835 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 0.4682. Min Range: -0.4682

Max Act: 0.4135. Min Act: -0.0000

Data Index: 636963 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.4682. Min Range: -0.4682

Max Act: 0.4176. Min Act: -0.0000

Data Index: 634277 (C4 (Web Text))

Max Activating Token Index: 792