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

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

Neuron 2256 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0814. Min Act: -0.0002

Data Index: 450765 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0707. Min Act: -0.0002

Data Index: 244529 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0648. Min Act: -0.0002

Data Index: 1558093 (Python Code)

Max Activating Token Index: 863

Text #3

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0657. Min Act: -0.0002

Data Index: 1441610 (Python Code)

Max Activating Token Index: 432

Text #4

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1527314 (Python Code)

Max Activating Token Index: 350

Text #5

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0619. Min Act: -0.0002

Data Index: 668769 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0609. Min Act: -0.0002

Data Index: 752911 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0629. Min Act: -0.0002

Data Index: 201351 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0598. Min Act: -0.0002

Data Index: 338548 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0583. Min Act: -0.0002

Data Index: 994062 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1239363 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1224795 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1401834 (Python Code)

Max Activating Token Index: 459

Text #13

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0557. Min Act: -0.0002

Data Index: 81954 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1273595 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1446150 (Python Code)

Max Activating Token Index: 477

Text #16

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0550. Min Act: -0.0002

Data Index: 5055 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0524. Min Act: -0.0002

Data Index: 648166 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0566. Min Act: -0.0002

Data Index: 718208 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1470520 (Python Code)

Max Activating Token Index: 928