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

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

Neuron 187 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: 0.0660. Min Range: -0.0660

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1339745 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0633. Min Act: -0.0002

Data Index: 214836 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0609. Min Act: -0.0002

Data Index: 863440 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1508182 (Python Code)

Max Activating Token Index: 302

Text #4

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1215485 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0591. Min Act: -0.0002

Data Index: 689725 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1595046 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0579. Min Act: -0.0002

Data Index: 262565 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0558. Min Act: -0.0002

Data Index: 851290 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0564. Min Act: -0.0002

Data Index: 1080219 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0550. Min Act: -0.0002

Data Index: 832462 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1282530 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0542. Min Act: -0.0002

Data Index: 295715 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0548. Min Act: -0.0002

Data Index: 113113 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0549. Min Act: -0.0002

Data Index: 72147 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0554. Min Act: -0.0002

Data Index: 738953 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1434911 (Python Code)

Max Activating Token Index: 155

Text #17

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0537. Min Act: -0.0003

Data Index: 481793 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0549. Min Act: -0.0002

Data Index: 720642 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1479654 (Python Code)

Max Activating Token Index: 419