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

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

Neuron 2621 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: 0.8771. Min Range: -0.8771

Max Act: 0.8771. Min Act: -0.0002

Data Index: 1608630 (Python Code)

Max Activating Token Index: 89

Text #1

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.8595. Min Act: -0.0002

Data Index: 1370269 (Python Code)

Max Activating Token Index: 556

Text #2

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.8563. Min Act: -0.0002

Data Index: 1405303 (Python Code)

Max Activating Token Index: 694

Text #3

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.8646. Min Act: -0.0002

Data Index: 1435718 (Python Code)

Max Activating Token Index: 549

Text #4

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.8556. Min Act: -0.0002

Data Index: 1448366 (Python Code)

Max Activating Token Index: 801

Text #5

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.8755. Min Act: -0.0002

Data Index: 1425328 (Python Code)

Max Activating Token Index: 144

Text #6

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.8472. Min Act: -0.0002

Data Index: 1378142 (Python Code)

Max Activating Token Index: 611

Text #7

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.8607. Min Act: -0.0002

Data Index: 1500123 (Python Code)

Max Activating Token Index: 497

Text #8

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.8264. Min Act: -0.0002

Data Index: 1584332 (Python Code)

Max Activating Token Index: 846

Text #9

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.8353. Min Act: -0.0002

Data Index: 1430598 (Python Code)

Max Activating Token Index: 431

Text #10

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.8431. Min Act: -0.0002

Data Index: 1626267 (Python Code)

Max Activating Token Index: 466

Text #11

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.8358. Min Act: -0.0002

Data Index: 1440889 (Python Code)

Max Activating Token Index: 334

Text #12

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.8247. Min Act: -0.0002

Data Index: 1428016 (Python Code)

Max Activating Token Index: 814

Text #13

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.8168. Min Act: -0.0002

Data Index: 1621183 (Python Code)

Max Activating Token Index: 883

Text #14

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.8238. Min Act: -0.0002

Data Index: 1446648 (Python Code)

Max Activating Token Index: 276

Text #15

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.8203. Min Act: -0.0002

Data Index: 1601104 (Python Code)

Max Activating Token Index: 237

Text #16

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.8241. Min Act: -0.0002

Data Index: 1525793 (Python Code)

Max Activating Token Index: 687

Text #17

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.8162. Min Act: -0.0002

Data Index: 1466377 (Python Code)

Max Activating Token Index: 260

Text #18

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.8184. Min Act: -0.0002

Data Index: 1370375 (Python Code)

Max Activating Token Index: 564

Text #19

Max Range: 0.8771. Min Range: -0.8771

Max Act: 0.8165. Min Act: -0.0002

Data Index: 1624166 (Python Code)

Max Activating Token Index: 904