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

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

Neuron 1316 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: 0.1894. Min Range: -0.1894

Max Act: 0.1894. Min Act: -0.0002

Data Index: 783441 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1745. Min Act: -0.0002

Data Index: 1256670 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1680. Min Act: -0.0002

Data Index: 47693 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1626. Min Act: -0.0002

Data Index: 1293742 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1584. Min Act: -0.0002

Data Index: 513555 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1592. Min Act: -0.0002

Data Index: 277733 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1552. Min Act: -0.0002

Data Index: 867214 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1562. Min Act: -0.0002

Data Index: 576440 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1509. Min Act: -0.0002

Data Index: 1294967 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1390. Min Act: -0.0002

Data Index: 727473 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1368. Min Act: -0.0002

Data Index: 916747 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1400. Min Act: -0.0002

Data Index: 240343 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1391. Min Act: -0.0002

Data Index: 84308 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1344. Min Act: -0.0002

Data Index: 1456366 (Python Code)

Max Activating Token Index: 900

Text #14

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1353. Min Act: -0.0002

Data Index: 1431142 (Python Code)

Max Activating Token Index: 92

Text #15

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1355. Min Act: -0.0002

Data Index: 1434013 (Python Code)

Max Activating Token Index: 945

Text #16

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1371. Min Act: -0.0002

Data Index: 75806 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1337. Min Act: -0.0002

Data Index: 1193830 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1360. Min Act: -0.0002

Data Index: 1052729 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1319. Min Act: -0.0002

Data Index: 1572056 (Python Code)

Max Activating Token Index: 989