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

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

Neuron 3378 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: 0.0700. Min Range: -0.0700

Max Act: 0.0700. Min Act: -0.0002

Data Index: 1501997 (Python Code)

Max Activating Token Index: 607

Text #1

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1614909 (Python Code)

Max Activating Token Index: 208

Text #2

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1382104 (Python Code)

Max Activating Token Index: 125

Text #3

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0678. Min Act: -0.0002

Data Index: 44343 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1624031 (Python Code)

Max Activating Token Index: 223

Text #5

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0677. Min Act: -0.0002

Data Index: 657219 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1203129 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1054795 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0607. Min Act: -0.0002

Data Index: 128116 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0600. Min Act: -0.0002

Data Index: 762273 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1251498 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1520527 (Python Code)

Max Activating Token Index: 422

Text #12

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0610. Min Act: -0.0002

Data Index: 417875 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1538324 (Python Code)

Max Activating Token Index: 795

Text #14

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1459297 (Python Code)

Max Activating Token Index: 525

Text #15

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1462056 (Python Code)

Max Activating Token Index: 321

Text #16

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1063658 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0557. Min Act: -0.0002

Data Index: 832623 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0575. Min Act: -0.0002

Data Index: 1576421 (Python Code)

Max Activating Token Index: 831

Text #19

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1553080 (Python Code)

Max Activating Token Index: 53