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

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

Neuron 154 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: 0.0739. Min Range: -0.0739

Max Act: 0.0739. Min Act: -0.0002

Data Index: 332330 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0713. Min Act: -0.0002

Data Index: 1469997 (Python Code)

Max Activating Token Index: 184

Text #2

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0699. Min Act: -0.0002

Data Index: 825672 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0690. Min Act: -0.0002

Data Index: 59735 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0691. Min Act: -0.0002

Data Index: 966724 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0657. Min Act: -0.0002

Data Index: 743900 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1591190 (Python Code)

Max Activating Token Index: 966

Text #7

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1243438 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0642. Min Act: -0.0002

Data Index: 880680 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0646. Min Act: -0.0002

Data Index: 15161 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0607. Min Act: -0.0002

Data Index: 904316 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0626. Min Act: -0.0002

Data Index: 1281350 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0619. Min Act: -0.0002

Data Index: 263821 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0600. Min Act: -0.0002

Data Index: 519148 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0590. Min Act: -0.0002

Data Index: 91772 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1607528 (Python Code)

Max Activating Token Index: 84

Text #16

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1632155 (Python Code)

Max Activating Token Index: 170

Text #17

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0606. Min Act: -0.0002

Data Index: 355 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1321430 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0592. Min Act: -0.0002

Data Index: 595602 (C4 (Web Text))

Max Activating Token Index: 510