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

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

Neuron 4349 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: 0.8319. Min Range: -0.8319

Max Act: 0.8319. Min Act: -0.0002

Data Index: 1598910 (Python Code)

Max Activating Token Index: 227

Text #1

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.8131. Min Act: -0.0002

Data Index: 1635356 (Python Code)

Max Activating Token Index: 556

Text #2

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7806. Min Act: -0.0002

Data Index: 1622112 (Python Code)

Max Activating Token Index: 771

Text #3

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7706. Min Act: -0.0002

Data Index: 1439237 (Python Code)

Max Activating Token Index: 136

Text #4

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7519. Min Act: -0.0002

Data Index: 1365089 (Python Code)

Max Activating Token Index: 601

Text #5

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7761. Min Act: -0.0002

Data Index: 1395146 (Python Code)

Max Activating Token Index: 267

Text #6

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7556. Min Act: -0.0002

Data Index: 1372839 (Python Code)

Max Activating Token Index: 211

Text #7

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7607. Min Act: -0.0002

Data Index: 1393008 (Python Code)

Max Activating Token Index: 614

Text #8

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7634. Min Act: -0.0002

Data Index: 1386032 (Python Code)

Max Activating Token Index: 20

Text #9

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7430. Min Act: -0.0002

Data Index: 1496416 (Python Code)

Max Activating Token Index: 909

Text #10

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7497. Min Act: -0.0002

Data Index: 1443264 (Python Code)

Max Activating Token Index: 234

Text #11

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7355. Min Act: -0.0002

Data Index: 1544008 (Python Code)

Max Activating Token Index: 879

Text #12

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7350. Min Act: -0.0002

Data Index: 1407814 (Python Code)

Max Activating Token Index: 595

Text #13

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7468. Min Act: -0.0002

Data Index: 1488008 (Python Code)

Max Activating Token Index: 788

Text #14

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7398. Min Act: -0.0002

Data Index: 1606691 (Python Code)

Max Activating Token Index: 629

Text #15

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7385. Min Act: -0.0002

Data Index: 1427043 (Python Code)

Max Activating Token Index: 770

Text #16

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7445. Min Act: -0.0002

Data Index: 1419347 (Python Code)

Max Activating Token Index: 250

Text #17

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7236. Min Act: -0.0002

Data Index: 1575625 (Python Code)

Max Activating Token Index: 132

Text #18

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7157. Min Act: -0.0002

Data Index: 1410166 (Python Code)

Max Activating Token Index: 342

Text #19

Max Range: 0.8319. Min Range: -0.8319

Max Act: 0.7225. Min Act: -0.0002

Data Index: 1518165 (Python Code)

Max Activating Token Index: 359