Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2796 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.3179. Min Act: -0.0001

Data Index: 84277 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.3044. Min Act: -0.0001

Data Index: 1554704 (Python Code)

Max Activating Token Index: 130

Text #2

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2779. Min Act: -0.0001

Data Index: 1594487 (Python Code)

Max Activating Token Index: 172

Text #3

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2750. Min Act: -0.0001

Data Index: 1541577 (Python Code)

Max Activating Token Index: 33

Text #4

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2756. Min Act: -0.0001

Data Index: 1402309 (Python Code)

Max Activating Token Index: 82

Text #5

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2748. Min Act: -0.0001

Data Index: 1475634 (Python Code)

Max Activating Token Index: 161

Text #6

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2498. Min Act: -0.0001

Data Index: 1597773 (Python Code)

Max Activating Token Index: 170

Text #7

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2750. Min Act: -0.0001

Data Index: 1623517 (Python Code)

Max Activating Token Index: 18

Text #8

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2759. Min Act: -0.0001

Data Index: 1650817 (Python Code)

Max Activating Token Index: 191

Text #9

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2617. Min Act: -0.0001

Data Index: 1523942 (Python Code)

Max Activating Token Index: 107

Text #10

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2623. Min Act: -0.0001

Data Index: 1514564 (Python Code)

Max Activating Token Index: 200

Text #11

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2567. Min Act: -0.0001

Data Index: 1513397 (Python Code)

Max Activating Token Index: 176

Text #12

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2392. Min Act: -0.0001

Data Index: 863363 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2557. Min Act: -0.0001

Data Index: 1605469 (Python Code)

Max Activating Token Index: 82

Text #14

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2189. Min Act: -0.0001

Data Index: 566110 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2536. Min Act: -0.0001

Data Index: 230649 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2607. Min Act: -0.0001

Data Index: 1535037 (Python Code)

Max Activating Token Index: 164

Text #17

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2528. Min Act: -0.0001

Data Index: 1614945 (Python Code)

Max Activating Token Index: 101

Text #18

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2519. Min Act: -0.0001

Data Index: 1542295 (Python Code)

Max Activating Token Index: 96

Text #19

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2553. Min Act: -0.0001

Data Index: 778871 (C4 (Web Text))

Max Activating Token Index: 890