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

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

Neuron 4809 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: 1.2967. Min Range: -1.2967

Max Act: 1.2967. Min Act: -0.0002

Data Index: 1393468 (Python Code)

Max Activating Token Index: 174

Text #1

Max Range: 1.2967. Min Range: -1.2967

Max Act: 1.1114. Min Act: -0.0002

Data Index: 1593521 (Python Code)

Max Activating Token Index: 910

Text #2

Max Range: 1.2967. Min Range: -1.2967

Max Act: 1.0856. Min Act: -0.0002

Data Index: 1641406 (Python Code)

Max Activating Token Index: 509

Text #3

Max Range: 1.2967. Min Range: -1.2967

Max Act: 1.1175. Min Act: -0.0002

Data Index: 1476668 (Python Code)

Max Activating Token Index: 139

Text #4

Max Range: 1.2967. Min Range: -1.2967

Max Act: 1.0689. Min Act: -0.0002

Data Index: 1560077 (Python Code)

Max Activating Token Index: 752

Text #5

Max Range: 1.2967. Min Range: -1.2967

Max Act: 1.0682. Min Act: -0.0002

Data Index: 1330531 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 1.2967. Min Range: -1.2967

Max Act: 1.0649. Min Act: -0.0002

Data Index: 1220513 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 1.2967. Min Range: -1.2967

Max Act: 1.0397. Min Act: -0.0002

Data Index: 1496738 (Python Code)

Max Activating Token Index: 262

Text #8

Max Range: 1.2967. Min Range: -1.2967

Max Act: 1.0183. Min Act: -0.0002

Data Index: 1537320 (Python Code)

Max Activating Token Index: 263

Text #9

Max Range: 1.2967. Min Range: -1.2967

Max Act: 1.0611. Min Act: -0.0002

Data Index: 1438066 (Python Code)

Max Activating Token Index: 796

Text #10

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.9965. Min Act: -0.0002

Data Index: 1586765 (Python Code)

Max Activating Token Index: 493

Text #11

Max Range: 1.2967. Min Range: -1.2967

Max Act: 1.0047. Min Act: -0.0002

Data Index: 1519178 (Python Code)

Max Activating Token Index: 216

Text #12

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.9927. Min Act: -0.0002

Data Index: 1547965 (Python Code)

Max Activating Token Index: 196

Text #13

Max Range: 1.2967. Min Range: -1.2967

Max Act: 1.0001. Min Act: -0.0002

Data Index: 1579899 (Python Code)

Max Activating Token Index: 91

Text #14

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.9711. Min Act: -0.0002

Data Index: 1378443 (Python Code)

Max Activating Token Index: 331

Text #15

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.9738. Min Act: -0.0002

Data Index: 1425553 (Python Code)

Max Activating Token Index: 210

Text #16

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.9696. Min Act: -0.0002

Data Index: 929118 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.9742. Min Act: -0.0002

Data Index: 1656427 (Python Code)

Max Activating Token Index: 358

Text #18

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.9718. Min Act: -0.0002

Data Index: 707687 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 1.2967. Min Range: -1.2967

Max Act: 0.9773. Min Act: -0.0002

Data Index: 1517486 (Python Code)

Max Activating Token Index: 583