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

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

Neuron 1355 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8270. Min Range: -4.8270

Max Act: 4.8270. Min Act: -0.0000

Data Index: 363988 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 4.8270. Min Range: -4.8270

Max Act: 4.5804. Min Act: -0.0000

Data Index: 98326 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 4.8270. Min Range: -4.8270

Max Act: 4.3488. Min Act: -0.0000

Data Index: 577321 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 4.8270. Min Range: -4.8270

Max Act: 4.2880. Min Act: -0.0000

Data Index: 1193383 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 4.8270. Min Range: -4.8270

Max Act: 4.0795. Min Act: -0.0000

Data Index: 928910 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 4.8270. Min Range: -4.8270

Max Act: 4.2336. Min Act: -0.0000

Data Index: 12345 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 4.8270. Min Range: -4.8270

Max Act: 4.3675. Min Act: -0.0000

Data Index: 1076872 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 4.8270. Min Range: -4.8270

Max Act: 4.2328. Min Act: -0.0000

Data Index: 948039 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 4.8270. Min Range: -4.8270

Max Act: 4.2261. Min Act: -0.0000

Data Index: 780992 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 4.8270. Min Range: -4.8270

Max Act: 4.0279. Min Act: -0.0000

Data Index: 416964 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 4.8270. Min Range: -4.8270

Max Act: 4.1745. Min Act: -0.0000

Data Index: 1345018 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 4.8270. Min Range: -4.8270

Max Act: 4.1805. Min Act: -0.0000

Data Index: 460318 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 4.8270. Min Range: -4.8270

Max Act: 4.1158. Min Act: -0.0000

Data Index: 1077556 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 4.8270. Min Range: -4.8270

Max Act: 4.0988. Min Act: -0.0000

Data Index: 737988 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 4.8270. Min Range: -4.8270

Max Act: 4.4351. Min Act: -0.0000

Data Index: 605298 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 4.8270. Min Range: -4.8270

Max Act: 3.8544. Min Act: -0.0000

Data Index: 1321530 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 4.8270. Min Range: -4.8270

Max Act: 4.1903. Min Act: -0.0000

Data Index: 675148 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 4.8270. Min Range: -4.8270

Max Act: 4.0214. Min Act: -0.0000

Data Index: 305347 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 4.8270. Min Range: -4.8270

Max Act: 3.9551. Min Act: -0.0000

Data Index: 116990 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 4.8270. Min Range: -4.8270

Max Act: 3.9088. Min Act: -0.0000

Data Index: 548696 (C4 (Web Text))

Max Activating Token Index: 76