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

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

Neuron 2622 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8922. Min Range: -1.8922

Max Act: 1.8922. Min Act: -0.0001

Data Index: 1457778 (Python Code)

Max Activating Token Index: 108

Text #1

Max Range: 1.8922. Min Range: -1.8922

Max Act: 1.4343. Min Act: -0.0001

Data Index: 149711 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 1.8922. Min Range: -1.8922

Max Act: 1.5371. Min Act: -0.0001

Data Index: 1481882 (Python Code)

Max Activating Token Index: 944

Text #3

Max Range: 1.8922. Min Range: -1.8922

Max Act: 1.1493. Min Act: -0.0001

Data Index: 1459399 (Python Code)

Max Activating Token Index: 892

Text #4

Max Range: 1.8922. Min Range: -1.8922

Max Act: 1.1298. Min Act: -0.0001

Data Index: 1502621 (Python Code)

Max Activating Token Index: 832

Text #5

Max Range: 1.8922. Min Range: -1.8922

Max Act: 1.0164. Min Act: -0.0001

Data Index: 1476856 (Python Code)

Max Activating Token Index: 113

Text #6

Max Range: 1.8922. Min Range: -1.8922

Max Act: 0.8096. Min Act: -0.0001

Data Index: 1375573 (Python Code)

Max Activating Token Index: 875

Text #7

Max Range: 1.8922. Min Range: -1.8922

Max Act: 0.9471. Min Act: -0.0001

Data Index: 1639828 (Python Code)

Max Activating Token Index: 134

Text #8

Max Range: 1.8922. Min Range: -1.8922

Max Act: 1.1130. Min Act: -0.0001

Data Index: 1648699 (Python Code)

Max Activating Token Index: 63

Text #9

Max Range: 1.8922. Min Range: -1.8922

Max Act: 0.8871. Min Act: -0.0001

Data Index: 800026 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 1.8922. Min Range: -1.8922

Max Act: 0.8614. Min Act: -0.0001

Data Index: 1610745 (Python Code)

Max Activating Token Index: 144

Text #11

Max Range: 1.8922. Min Range: -1.8922

Max Act: 0.8728. Min Act: -0.0001

Data Index: 1623092 (Python Code)

Max Activating Token Index: 817

Text #12

Max Range: 1.8922. Min Range: -1.8922

Max Act: 0.8665. Min Act: -0.0001

Data Index: 1533747 (Python Code)

Max Activating Token Index: 156

Text #13

Max Range: 1.8922. Min Range: -1.8922

Max Act: 0.9418. Min Act: -0.0001

Data Index: 1564530 (Python Code)

Max Activating Token Index: 299

Text #14

Max Range: 1.8922. Min Range: -1.8922

Max Act: 0.8906. Min Act: -0.0001

Data Index: 1406968 (Python Code)

Max Activating Token Index: 543

Text #15

Max Range: 1.8922. Min Range: -1.8922

Max Act: 1.0813. Min Act: -0.0001

Data Index: 1645378 (Python Code)

Max Activating Token Index: 631

Text #16

Max Range: 1.8922. Min Range: -1.8922

Max Act: 0.7800. Min Act: -0.0001

Data Index: 1388858 (Python Code)

Max Activating Token Index: 663

Text #17

Max Range: 1.8922. Min Range: -1.8922

Max Act: 0.8941. Min Act: -0.0001

Data Index: 1057861 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 1.8922. Min Range: -1.8922

Max Act: 0.7426. Min Act: -0.0001

Data Index: 1445918 (Python Code)

Max Activating Token Index: 692

Text #19

Max Range: 1.8922. Min Range: -1.8922

Max Act: 0.8807. Min Act: -0.0001

Data Index: 1362874 (Python Code)

Max Activating Token Index: 134