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

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

Neuron 3208 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: 0.3809. Min Range: -0.3809

Max Act: 0.3809. Min Act: -0.0002

Data Index: 1620137 (Python Code)

Max Activating Token Index: 291

Text #1

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3664. Min Act: -0.0002

Data Index: 1463530 (Python Code)

Max Activating Token Index: 991

Text #2

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3660. Min Act: -0.0002

Data Index: 1436535 (Python Code)

Max Activating Token Index: 951

Text #3

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3675. Min Act: -0.0002

Data Index: 1519977 (Python Code)

Max Activating Token Index: 282

Text #4

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3630. Min Act: -0.0002

Data Index: 1634691 (Python Code)

Max Activating Token Index: 356

Text #5

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3552. Min Act: -0.0002

Data Index: 1375970 (Python Code)

Max Activating Token Index: 444

Text #6

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3595. Min Act: -0.0002

Data Index: 1375811 (Python Code)

Max Activating Token Index: 163

Text #7

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3557. Min Act: -0.0002

Data Index: 1556008 (Python Code)

Max Activating Token Index: 388

Text #8

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3597. Min Act: -0.0002

Data Index: 1573411 (Python Code)

Max Activating Token Index: 885

Text #9

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3532. Min Act: -0.0002

Data Index: 1558257 (Python Code)

Max Activating Token Index: 467

Text #10

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3584. Min Act: -0.0002

Data Index: 1656866 (Python Code)

Max Activating Token Index: 198

Text #11

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3514. Min Act: -0.0002

Data Index: 1552677 (Python Code)

Max Activating Token Index: 327

Text #12

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3511. Min Act: -0.0002

Data Index: 1503971 (Python Code)

Max Activating Token Index: 662

Text #13

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3562. Min Act: -0.0002

Data Index: 1393184 (Python Code)

Max Activating Token Index: 570

Text #14

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3553. Min Act: -0.0002

Data Index: 1443538 (Python Code)

Max Activating Token Index: 228

Text #15

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3496. Min Act: -0.0002

Data Index: 1563940 (Python Code)

Max Activating Token Index: 607

Text #16

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3492. Min Act: -0.0002

Data Index: 1550272 (Python Code)

Max Activating Token Index: 282

Text #17

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3444. Min Act: -0.0002

Data Index: 1630093 (Python Code)

Max Activating Token Index: 600

Text #18

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3473. Min Act: -0.0002

Data Index: 829427 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.3809. Min Range: -0.3809

Max Act: 0.3503. Min Act: -0.0002

Data Index: 1414796 (Python Code)

Max Activating Token Index: 297