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

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

Neuron 4190 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: 0.0675. Min Range: -0.0675

Max Act: 0.0675. Min Act: -0.0002

Data Index: 263052 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1381008 (Python Code)

Max Activating Token Index: 967

Text #2

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0648. Min Act: -0.0002

Data Index: 943760 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0661. Min Act: -0.0002

Data Index: 388520 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0650. Min Act: -0.0002

Data Index: 1577905 (Python Code)

Max Activating Token Index: 259

Text #5

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0652. Min Act: -0.0002

Data Index: 90581 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0630. Min Act: -0.0002

Data Index: 1539904 (Python Code)

Max Activating Token Index: 327

Text #7

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0643. Min Act: -0.0002

Data Index: 417001 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0632. Min Act: -0.0002

Data Index: 603133 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0622. Min Act: -0.0002

Data Index: 202330 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1635044 (Python Code)

Max Activating Token Index: 104

Text #11

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0633. Min Act: -0.0002

Data Index: 1539198 (Python Code)

Max Activating Token Index: 913

Text #12

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0622. Min Act: -0.0002

Data Index: 513985 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0618. Min Act: -0.0002

Data Index: 228747 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1379997 (Python Code)

Max Activating Token Index: 463

Text #15

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0626. Min Act: -0.0002

Data Index: 1387029 (Python Code)

Max Activating Token Index: 650

Text #16

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0618. Min Act: -0.0002

Data Index: 133756 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0610. Min Act: -0.0002

Data Index: 431145 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0622. Min Act: -0.0002

Data Index: 633937 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0618. Min Act: -0.0002

Data Index: 203227 (C4 (Web Text))

Max Activating Token Index: 905