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

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

Neuron 5221 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: 0.0627. Min Range: -0.0627

Max Act: 0.0627. Min Act: -0.0001

Data Index: 1365139 (Python Code)

Max Activating Token Index: 16

Text #1

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0502. Min Act: -0.0001

Data Index: 7641 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0492. Min Act: -0.0001

Data Index: 32182 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0481. Min Act: -0.0001

Data Index: 1218261 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0482. Min Act: -0.0001

Data Index: 1438506 (Python Code)

Max Activating Token Index: 939

Text #5

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0472. Min Act: -0.0001

Data Index: 231636 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0464. Min Act: -0.0001

Data Index: 1346081 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0461. Min Act: -0.0001

Data Index: 1476916 (Python Code)

Max Activating Token Index: 55

Text #8

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0456. Min Act: -0.0001

Data Index: 1178519 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0453. Min Act: -0.0001

Data Index: 1446910 (Python Code)

Max Activating Token Index: 30

Text #10

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0441. Min Act: -0.0001

Data Index: 1620945 (Python Code)

Max Activating Token Index: 640

Text #11

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0453. Min Act: -0.0001

Data Index: 1395412 (Python Code)

Max Activating Token Index: 97

Text #12

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0436. Min Act: -0.0001

Data Index: 900856 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0445. Min Act: -0.0001

Data Index: 1050902 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0449. Min Act: -0.0001

Data Index: 1175030 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1490941 (Python Code)

Max Activating Token Index: 188

Text #16

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0428. Min Act: -0.0001

Data Index: 1556869 (Python Code)

Max Activating Token Index: 501

Text #17

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0438. Min Act: -0.0001

Data Index: 802112 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0414. Min Act: -0.0001

Data Index: 1549191 (Python Code)

Max Activating Token Index: 21

Text #19

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0407. Min Act: -0.0001

Data Index: 1363643 (Python Code)

Max Activating Token Index: 51