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

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

Neuron 550 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6620. Min Act: -0.0002

Data Index: 1381776 (Python Code)

Max Activating Token Index: 927

Text #1

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6662. Min Act: -0.0002

Data Index: 1436408 (Python Code)

Max Activating Token Index: 28

Text #2

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6328. Min Act: -0.0002

Data Index: 1625808 (Python Code)

Max Activating Token Index: 502

Text #3

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6378. Min Act: -0.0002

Data Index: 1580291 (Python Code)

Max Activating Token Index: 283

Text #4

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6334. Min Act: -0.0002

Data Index: 1590868 (Python Code)

Max Activating Token Index: 117

Text #5

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6227. Min Act: -0.0002

Data Index: 1405776 (Python Code)

Max Activating Token Index: 224

Text #6

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6303. Min Act: -0.0002

Data Index: 1499461 (Python Code)

Max Activating Token Index: 315

Text #7

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6328. Min Act: -0.0002

Data Index: 1530411 (Python Code)

Max Activating Token Index: 278

Text #8

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6187. Min Act: -0.0002

Data Index: 1554191 (Python Code)

Max Activating Token Index: 384

Text #9

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6188. Min Act: -0.0002

Data Index: 1602074 (Python Code)

Max Activating Token Index: 301

Text #10

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6192. Min Act: -0.0002

Data Index: 1369792 (Python Code)

Max Activating Token Index: 411

Text #11

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6173. Min Act: -0.0002

Data Index: 1504813 (Python Code)

Max Activating Token Index: 248

Text #12

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6199. Min Act: -0.0002

Data Index: 1477927 (Python Code)

Max Activating Token Index: 426

Text #13

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6145. Min Act: -0.0002

Data Index: 1522560 (Python Code)

Max Activating Token Index: 297

Text #14

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6142. Min Act: -0.0002

Data Index: 1601244 (Python Code)

Max Activating Token Index: 340

Text #15

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6185. Min Act: -0.0002

Data Index: 1547982 (Python Code)

Max Activating Token Index: 301

Text #16

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6088. Min Act: -0.0002

Data Index: 1506447 (Python Code)

Max Activating Token Index: 209

Text #17

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6120. Min Act: -0.0002

Data Index: 1459140 (Python Code)

Max Activating Token Index: 257

Text #18

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6037. Min Act: -0.0002

Data Index: 1571013 (Python Code)

Max Activating Token Index: 99

Text #19

Max Range: 0.6662. Min Range: -0.6662

Max Act: 0.6112. Min Act: -0.0002

Data Index: 1530516 (Python Code)

Max Activating Token Index: 742