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

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

Neuron 4892 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.9266. Min Act: -0.0000

Data Index: 614974 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.6557. Min Act: -0.0000

Data Index: 393822 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.4828. Min Act: -0.0000

Data Index: 830060 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.4650. Min Act: -0.0000

Data Index: 484893 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.4396. Min Act: -0.0000

Data Index: 797923 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.4917. Min Act: -0.0000

Data Index: 1302857 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.3541. Min Act: -0.0000

Data Index: 891888 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.2519. Min Act: -0.0000

Data Index: 1613288 (Python Code)

Max Activating Token Index: 279

Text #8

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.3840. Min Act: -0.0000

Data Index: 77802 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.3933. Min Act: -0.0000

Data Index: 685028 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.4021. Min Act: -0.0000

Data Index: 1626811 (Python Code)

Max Activating Token Index: 490

Text #11

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.3870. Min Act: -0.0000

Data Index: 1001198 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.3455. Min Act: -0.0000

Data Index: 236715 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.2467. Min Act: 0.0000

Data Index: 1333140 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.2664. Min Act: -0.0000

Data Index: 779007 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.2650. Min Act: -0.0000

Data Index: 637753 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.1820. Min Act: -0.0000

Data Index: 354140 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.1747. Min Act: -0.0000

Data Index: 889640 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.1497. Min Act: -0.0000

Data Index: 1218622 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 1.9266. Min Range: -1.9266

Max Act: 1.1251. Min Act: -0.0000

Data Index: 344784 (C4 (Web Text))

Max Activating Token Index: 327