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

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

Neuron 4384 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: 0.0688. Min Range: -0.0688

Max Act: 0.0688. Min Act: -0.0002

Data Index: 1533836 (Python Code)

Max Activating Token Index: 490

Text #1

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0640. Min Act: -0.0002

Data Index: 1028143 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1467834 (Python Code)

Max Activating Token Index: 246

Text #3

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0608. Min Act: -0.0002

Data Index: 222440 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0582. Min Act: -0.0002

Data Index: 1549249 (Python Code)

Max Activating Token Index: 111

Text #5

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0572. Min Act: -0.0002

Data Index: 990370 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0558. Min Act: -0.0002

Data Index: 516098 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1504786 (Python Code)

Max Activating Token Index: 397

Text #8

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1005484 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1400700 (Python Code)

Max Activating Token Index: 339

Text #10

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1636268 (Python Code)

Max Activating Token Index: 316

Text #11

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1401531 (Python Code)

Max Activating Token Index: 390

Text #12

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0549. Min Act: -0.0002

Data Index: 311750 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1234902 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1349722 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0505. Min Act: -0.0002

Data Index: 106645 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0520. Min Act: -0.0002

Data Index: 759557 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1599005 (Python Code)

Max Activating Token Index: 117

Text #18

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1517477 (Python Code)

Max Activating Token Index: 58

Text #19

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0503. Min Act: -0.0002

Data Index: 745320 (C4 (Web Text))

Max Activating Token Index: 960