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

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

Neuron 770 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0734. Min Range: -2.0734

Max Act: 2.0734. Min Act: -0.0000

Data Index: 1434920 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.9830. Min Act: -0.0001

Data Index: 1640842 (Python Code)

Max Activating Token Index: 642

Text #2

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.7929. Min Act: -0.0000

Data Index: 1511536 (Python Code)

Max Activating Token Index: 7

Text #3

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.6911. Min Act: -0.0001

Data Index: 1488105 (Python Code)

Max Activating Token Index: 851

Text #4

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.6943. Min Act: -0.0001

Data Index: 1474098 (Python Code)

Max Activating Token Index: 43

Text #5

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.4828. Min Act: -0.0001

Data Index: 1600686 (Python Code)

Max Activating Token Index: 234

Text #6

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.5254. Min Act: -0.0000

Data Index: 1410924 (Python Code)

Max Activating Token Index: 70

Text #7

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.6511. Min Act: -0.0000

Data Index: 1363675 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.6013. Min Act: -0.0001

Data Index: 1629236 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.6620. Min Act: -0.0000

Data Index: 1621153 (Python Code)

Max Activating Token Index: 320

Text #10

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.5802. Min Act: -0.0000

Data Index: 1424097 (Python Code)

Max Activating Token Index: 241

Text #11

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.5371. Min Act: -0.0001

Data Index: 1568576 (Python Code)

Max Activating Token Index: 24

Text #12

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.7637. Min Act: -0.0000

Data Index: 1497517 (Python Code)

Max Activating Token Index: 236

Text #13

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.5451. Min Act: -0.0000

Data Index: 1433847 (Python Code)

Max Activating Token Index: 489

Text #14

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.3816. Min Act: -0.0000

Data Index: 1568492 (Python Code)

Max Activating Token Index: 875

Text #15

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.6549. Min Act: -0.0000

Data Index: 728973 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.3632. Min Act: -0.0001

Data Index: 160698 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.2973. Min Act: -0.0000

Data Index: 16840 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.4269. Min Act: -0.0000

Data Index: 1582003 (Python Code)

Max Activating Token Index: 5

Text #19

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.4328. Min Act: -0.0000

Data Index: 1429535 (Python Code)

Max Activating Token Index: 226