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

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

Neuron 2382 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: 0.1545. Min Range: -0.1545

Max Act: 0.1545. Min Act: -0.0002

Data Index: 1534114 (Python Code)

Max Activating Token Index: 592

Text #1

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1523. Min Act: -0.0002

Data Index: 1515453 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1482. Min Act: -0.0002

Data Index: 1592735 (Python Code)

Max Activating Token Index: 755

Text #3

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1472. Min Act: -0.0002

Data Index: 1626589 (Python Code)

Max Activating Token Index: 275

Text #4

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1498. Min Act: -0.0002

Data Index: 1431170 (Python Code)

Max Activating Token Index: 73

Text #5

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1405. Min Act: -0.0002

Data Index: 1550825 (Python Code)

Max Activating Token Index: 44

Text #6

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1438. Min Act: -0.0002

Data Index: 1546441 (Python Code)

Max Activating Token Index: 561

Text #7

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1428. Min Act: -0.0002

Data Index: 1472627 (Python Code)

Max Activating Token Index: 428

Text #8

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1384. Min Act: -0.0002

Data Index: 1508022 (Python Code)

Max Activating Token Index: 606

Text #9

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1405. Min Act: -0.0002

Data Index: 1471928 (Python Code)

Max Activating Token Index: 770

Text #10

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1376. Min Act: -0.0002

Data Index: 1640696 (Python Code)

Max Activating Token Index: 10

Text #11

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1349. Min Act: -0.0002

Data Index: 948346 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1356. Min Act: -0.0002

Data Index: 1516831 (Python Code)

Max Activating Token Index: 15

Text #13

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1352. Min Act: -0.0002

Data Index: 1455704 (Python Code)

Max Activating Token Index: 608

Text #14

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1362. Min Act: -0.0002

Data Index: 1504939 (Python Code)

Max Activating Token Index: 835

Text #15

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1358. Min Act: -0.0002

Data Index: 1586852 (Python Code)

Max Activating Token Index: 334

Text #16

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1342. Min Act: -0.0002

Data Index: 1652173 (Python Code)

Max Activating Token Index: 724

Text #17

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1323. Min Act: -0.0002

Data Index: 1049349 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1316. Min Act: -0.0002

Data Index: 1503751 (Python Code)

Max Activating Token Index: 23

Text #19

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1328. Min Act: -0.0002

Data Index: 1516446 (Python Code)

Max Activating Token Index: 23