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

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

Neuron 4941 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: 0.7005. Min Range: -0.7005

Max Act: 0.7005. Min Act: -0.0002

Data Index: 1484355 (Python Code)

Max Activating Token Index: 12

Text #1

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.6950. Min Act: -0.0002

Data Index: 1598261 (Python Code)

Max Activating Token Index: 240

Text #2

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.6700. Min Act: -0.0002

Data Index: 1640459 (Python Code)

Max Activating Token Index: 214

Text #3

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.6619. Min Act: -0.0002

Data Index: 1548240 (Python Code)

Max Activating Token Index: 62

Text #4

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.6378. Min Act: -0.0002

Data Index: 1629527 (Python Code)

Max Activating Token Index: 248

Text #5

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.6238. Min Act: -0.0002

Data Index: 1467887 (Python Code)

Max Activating Token Index: 8

Text #6

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.6082. Min Act: -0.0002

Data Index: 1623869 (Python Code)

Max Activating Token Index: 720

Text #7

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.6193. Min Act: -0.0002

Data Index: 1643807 (Python Code)

Max Activating Token Index: 114

Text #8

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.5918. Min Act: -0.0002

Data Index: 1522008 (Python Code)

Max Activating Token Index: 525

Text #9

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.5813. Min Act: -0.0002

Data Index: 1419844 (Python Code)

Max Activating Token Index: 1001

Text #10

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.5769. Min Act: -0.0002

Data Index: 1652482 (Python Code)

Max Activating Token Index: 469

Text #11

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.5693. Min Act: -0.0002

Data Index: 1608177 (Python Code)

Max Activating Token Index: 454

Text #12

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.5505. Min Act: -0.0002

Data Index: 1464220 (Python Code)

Max Activating Token Index: 734

Text #13

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.5442. Min Act: -0.0002

Data Index: 1367075 (Python Code)

Max Activating Token Index: 826

Text #14

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.5490. Min Act: -0.0002

Data Index: 1571434 (Python Code)

Max Activating Token Index: 300

Text #15

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.5425. Min Act: -0.0002

Data Index: 1402158 (Python Code)

Max Activating Token Index: 35

Text #16

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.5501. Min Act: -0.0002

Data Index: 1529072 (Python Code)

Max Activating Token Index: 877

Text #17

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.5528. Min Act: -0.0002

Data Index: 1572365 (Python Code)

Max Activating Token Index: 10

Text #18

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.5432. Min Act: -0.0002

Data Index: 1536508 (Python Code)

Max Activating Token Index: 15

Text #19

Max Range: 0.7005. Min Range: -0.7005

Max Act: 0.5452. Min Act: -0.0002

Data Index: 1533834 (Python Code)

Max Activating Token Index: 176