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

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

Neuron 1480 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: 0.5433. Min Range: -0.5433

Max Act: 0.5433. Min Act: -0.0000

Data Index: 224109 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.5063. Min Act: -0.0000

Data Index: 176357 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.5405. Min Act: -0.0000

Data Index: 644336 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4890. Min Act: -0.0000

Data Index: 1244663 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4535. Min Act: -0.0000

Data Index: 561358 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4076. Min Act: -0.0000

Data Index: 515173 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4515. Min Act: -0.0000

Data Index: 421958 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1247991 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1280169 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4465. Min Act: -0.0000

Data Index: 998541 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4416. Min Act: -0.0000

Data Index: 738123 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4108. Min Act: -0.0000

Data Index: 1100362 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4038. Min Act: -0.0000

Data Index: 737638 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4279. Min Act: -0.0000

Data Index: 319049 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4104. Min Act: -0.0000

Data Index: 133245 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1152976 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4329. Min Act: -0.0000

Data Index: 374093 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.3790. Min Act: -0.0000

Data Index: 26194 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4058. Min Act: -0.0000

Data Index: 611046 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4023. Min Act: -0.0000

Data Index: 1111186 (C4 (Web Text))

Max Activating Token Index: 768