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

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

Neuron 336 in Layer 0

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: 0.1160. Min Range: -0.1160

Max Act: 0.1160. Min Act: -0.0001

Data Index: 1510306 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0860. Min Act: -0.0001

Data Index: 1435972 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1541305 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0584. Min Act: -0.0001

Data Index: 1380361 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0569. Min Act: -0.0000

Data Index: 1406865 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0566. Min Act: -0.0001

Data Index: 1494546 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1496507 (Python Code)

Max Activating Token Index: 852

Text #7

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0562. Min Act: -0.0001

Data Index: 1503315 (Python Code)

Max Activating Token Index: 382

Text #8

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0568. Min Act: -0.0001

Data Index: 1398423 (Python Code)

Max Activating Token Index: 729

Text #9

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0537. Min Act: -0.0001

Data Index: 1592446 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0539. Min Act: -0.0001

Data Index: 1505282 (Python Code)

Max Activating Token Index: 955

Text #11

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0512. Min Act: -0.0001

Data Index: 1482367 (Python Code)

Max Activating Token Index: 549

Text #12

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0506. Min Act: -0.0001

Data Index: 1617251 (Python Code)

Max Activating Token Index: 216

Text #13

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0517. Min Act: -0.0001

Data Index: 1601916 (Python Code)

Max Activating Token Index: 474

Text #14

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0497. Min Act: -0.0001

Data Index: 1609661 (Python Code)

Max Activating Token Index: 348

Text #15

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0497. Min Act: -0.0001

Data Index: 1638420 (Python Code)

Max Activating Token Index: 111

Text #16

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0512. Min Act: -0.0001

Data Index: 1369244 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0483. Min Act: -0.0001

Data Index: 1482392 (Python Code)

Max Activating Token Index: 210

Text #18

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0496. Min Act: -0.0001

Data Index: 1428810 (Python Code)

Max Activating Token Index: 403

Text #19

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0484. Min Act: -0.0001

Data Index: 1500559 (Python Code)

Max Activating Token Index: 464