Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4454 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.8195. Min Range: -3.8195

Max Act: 3.8195. Min Act: -0.0000

Data Index: 988060 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 3.8195. Min Range: -3.8195

Max Act: 3.4482. Min Act: -0.0000

Data Index: 542165 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 3.8195. Min Range: -3.8195

Max Act: 3.2528. Min Act: -0.0000

Data Index: 838973 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 3.8195. Min Range: -3.8195

Max Act: 3.0317. Min Act: -0.0000

Data Index: 599526 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 3.8195. Min Range: -3.8195

Max Act: 3.1992. Min Act: -0.0000

Data Index: 1140458 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 3.8195. Min Range: -3.8195

Max Act: 2.9814. Min Act: -0.0000

Data Index: 229065 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 3.8195. Min Range: -3.8195

Max Act: 2.7074. Min Act: -0.0000

Data Index: 342445 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 3.8195. Min Range: -3.8195

Max Act: 2.7007. Min Act: -0.0000

Data Index: 389201 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 3.8195. Min Range: -3.8195

Max Act: 2.6206. Min Act: -0.0000

Data Index: 1182058 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 3.8195. Min Range: -3.8195

Max Act: 2.5176. Min Act: -0.0000

Data Index: 957265 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 3.8195. Min Range: -3.8195

Max Act: 2.3929. Min Act: -0.0000

Data Index: 166834 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 3.8195. Min Range: -3.8195

Max Act: 2.5086. Min Act: -0.0000

Data Index: 1283312 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 3.8195. Min Range: -3.8195

Max Act: 2.4766. Min Act: 0.0000

Data Index: 665693 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 3.8195. Min Range: -3.8195

Max Act: 2.4723. Min Act: -0.0000

Data Index: 82553 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 3.8195. Min Range: -3.8195

Max Act: 2.6018. Min Act: -0.0000

Data Index: 1005885 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 3.8195. Min Range: -3.8195

Max Act: 2.3358. Min Act: -0.0000

Data Index: 757487 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 3.8195. Min Range: -3.8195

Max Act: 2.3137. Min Act: -0.0000

Data Index: 1086472 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 3.8195. Min Range: -3.8195

Max Act: 2.3114. Min Act: -0.0000

Data Index: 41687 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 3.8195. Min Range: -3.8195

Max Act: 2.2994. Min Act: -0.0000

Data Index: 402795 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 3.8195. Min Range: -3.8195

Max Act: 2.2766. Min Act: -0.0000

Data Index: 511986 (C4 (Web Text))

Max Activating Token Index: 410