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

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

Neuron 5238 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: 0.0490. Min Range: -0.0490

Max Act: 0.0490. Min Act: -0.0001

Data Index: 1445848 (Python Code)

Max Activating Token Index: 27

Text #1

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0481. Min Act: -0.0001

Data Index: 1574519 (Python Code)

Max Activating Token Index: 29

Text #2

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0474. Min Act: -0.0001

Data Index: 1400940 (Python Code)

Max Activating Token Index: 14

Text #3

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0469. Min Act: -0.0001

Data Index: 1372488 (Python Code)

Max Activating Token Index: 16

Text #4

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0481. Min Act: -0.0001

Data Index: 1362014 (Python Code)

Max Activating Token Index: 20

Text #5

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0466. Min Act: -0.0001

Data Index: 1505715 (Python Code)

Max Activating Token Index: 13

Text #6

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1556289 (Python Code)

Max Activating Token Index: 22

Text #7

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0471. Min Act: -0.0001

Data Index: 1463543 (Python Code)

Max Activating Token Index: 18

Text #8

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1581704 (Python Code)

Max Activating Token Index: 27

Text #9

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0469. Min Act: -0.0001

Data Index: 1439118 (Python Code)

Max Activating Token Index: 24

Text #10

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0446. Min Act: -0.0001

Data Index: 1433059 (Python Code)

Max Activating Token Index: 32

Text #11

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0444. Min Act: -0.0001

Data Index: 1454318 (Python Code)

Max Activating Token Index: 28

Text #12

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0437. Min Act: -0.0001

Data Index: 1441578 (Python Code)

Max Activating Token Index: 28

Text #13

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0435. Min Act: -0.0001

Data Index: 1462110 (Python Code)

Max Activating Token Index: 17

Text #14

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0446. Min Act: -0.0001

Data Index: 1416309 (Python Code)

Max Activating Token Index: 30

Text #15

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0441. Min Act: -0.0001

Data Index: 1451742 (Python Code)

Max Activating Token Index: 13

Text #16

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0437. Min Act: -0.0001

Data Index: 1593123 (Python Code)

Max Activating Token Index: 25

Text #17

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0435. Min Act: -0.0001

Data Index: 1495732 (Python Code)

Max Activating Token Index: 11

Text #18

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1555269 (Python Code)

Max Activating Token Index: 13

Text #19

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0422. Min Act: -0.0001

Data Index: 1629466 (Python Code)

Max Activating Token Index: 13