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

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

Neuron 4679 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1730. Min Act: -0.0001

Data Index: 1388172 (Python Code)

Max Activating Token Index: 161

Text #1

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1519. Min Act: -0.0001

Data Index: 1420847 (Python Code)

Max Activating Token Index: 301

Text #2

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1491. Min Act: -0.0001

Data Index: 1558451 (Python Code)

Max Activating Token Index: 370

Text #3

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1501. Min Act: -0.0001

Data Index: 1477308 (Python Code)

Max Activating Token Index: 946

Text #4

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1322. Min Act: -0.0001

Data Index: 1574529 (Python Code)

Max Activating Token Index: 259

Text #5

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1426. Min Act: -0.0001

Data Index: 1633319 (Python Code)

Max Activating Token Index: 388

Text #6

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1367. Min Act: -0.0001

Data Index: 1446524 (Python Code)

Max Activating Token Index: 638

Text #7

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1301. Min Act: -0.0001

Data Index: 1621279 (Python Code)

Max Activating Token Index: 723

Text #8

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1293. Min Act: -0.0001

Data Index: 1552139 (Python Code)

Max Activating Token Index: 711

Text #9

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1345. Min Act: -0.0001

Data Index: 1400471 (Python Code)

Max Activating Token Index: 1002

Text #10

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1355. Min Act: -0.0001

Data Index: 1623273 (Python Code)

Max Activating Token Index: 517

Text #11

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1349. Min Act: -0.0001

Data Index: 1456536 (Python Code)

Max Activating Token Index: 467

Text #12

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1248. Min Act: -0.0001

Data Index: 1376460 (Python Code)

Max Activating Token Index: 852

Text #13

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1152. Min Act: -0.0001

Data Index: 1593910 (Python Code)

Max Activating Token Index: 678

Text #14

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1186. Min Act: -0.0001

Data Index: 1649728 (Python Code)

Max Activating Token Index: 202

Text #15

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1173. Min Act: -0.0001

Data Index: 1488877 (Python Code)

Max Activating Token Index: 322

Text #16

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1160. Min Act: -0.0001

Data Index: 1600023 (Python Code)

Max Activating Token Index: 285

Text #17

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1209. Min Act: -0.0001

Data Index: 1619142 (Python Code)

Max Activating Token Index: 278

Text #18

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1395544 (Python Code)

Max Activating Token Index: 283

Text #19

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1220. Min Act: -0.0001

Data Index: 921877 (C4 (Web Text))

Max Activating Token Index: 258