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

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

Neuron 922 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1629. Min Act: -0.0000

Data Index: 229683 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1674. Min Act: -0.0000

Data Index: 1585027 (Python Code)

Max Activating Token Index: 850

Text #2

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1548. Min Act: -0.0000

Data Index: 1404445 (Python Code)

Max Activating Token Index: 283

Text #3

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1594. Min Act: -0.0000

Data Index: 1634519 (Python Code)

Max Activating Token Index: 203

Text #4

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1536. Min Act: -0.0000

Data Index: 50295 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1485. Min Act: -0.0000

Data Index: 801590 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1465. Min Act: -0.0000

Data Index: 1442839 (Python Code)

Max Activating Token Index: 201

Text #7

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1480. Min Act: -0.0000

Data Index: 634927 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1327. Min Act: -0.0000

Data Index: 1388084 (Python Code)

Max Activating Token Index: 230

Text #9

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1345. Min Act: -0.0000

Data Index: 44584 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1364. Min Act: 0.0000

Data Index: 838165 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1314. Min Act: -0.0000

Data Index: 140296 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1348. Min Act: -0.0000

Data Index: 1199096 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1217. Min Act: -0.0000

Data Index: 1204822 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1237. Min Act: -0.0000

Data Index: 279360 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1564981 (Python Code)

Max Activating Token Index: 1006

Text #16

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1262. Min Act: -0.0000

Data Index: 321373 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1251. Min Act: -0.0000

Data Index: 308766 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1258. Min Act: -0.0000

Data Index: 486228 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1257. Min Act: -0.0000

Data Index: 971870 (C4 (Web Text))

Max Activating Token Index: 355