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

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

Neuron 2038 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0676. Min Act: -0.0001

Data Index: 741872 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0634. Min Act: -0.0001

Data Index: 381537 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0591. Min Act: -0.0001

Data Index: 515588 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0588. Min Act: -0.0001

Data Index: 239965 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0548. Min Act: -0.0001

Data Index: 432290 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0603. Min Act: -0.0001

Data Index: 853735 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1411565 (Python Code)

Max Activating Token Index: 482

Text #7

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1206261 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0600. Min Act: -0.0001

Data Index: 842281 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0566. Min Act: -0.0001

Data Index: 1300317 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0525. Min Act: -0.0001

Data Index: 1113806 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1316557 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1490241 (Python Code)

Max Activating Token Index: 173

Text #13

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0571. Min Act: -0.0001

Data Index: 1312844 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0549. Min Act: -0.0001

Data Index: 260779 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0548. Min Act: -0.0001

Data Index: 1404651 (Python Code)

Max Activating Token Index: 629

Text #16

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0581. Min Act: -0.0001

Data Index: 315060 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0468. Min Act: -0.0001

Data Index: 36256 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0529. Min Act: -0.0001

Data Index: 1059022 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0530. Min Act: -0.0001

Data Index: 33038 (C4 (Web Text))

Max Activating Token Index: 865