Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1859 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1035. Min Range: -2.1035

Max Act: 2.1035. Min Act: -0.0000

Data Index: 637021 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.9034. Min Act: -0.0000

Data Index: 1176704 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.9278. Min Act: -0.0000

Data Index: 223967 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.8670. Min Act: -0.0000

Data Index: 74342 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.7539. Min Act: -0.0000

Data Index: 213490 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.6597. Min Act: -0.0000

Data Index: 7596 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.7589. Min Act: -0.0000

Data Index: 1207607 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.8162. Min Act: -0.0000

Data Index: 642275 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.5551. Min Act: -0.0000

Data Index: 942590 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.8142. Min Act: -0.0000

Data Index: 598141 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.5599. Min Act: -0.0000

Data Index: 862939 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.6361. Min Act: -0.0000

Data Index: 1426346 (Python Code)

Max Activating Token Index: 282

Text #12

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.5443. Min Act: -0.0000

Data Index: 747308 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.4838. Min Act: -0.0000

Data Index: 1383849 (Python Code)

Max Activating Token Index: 839

Text #14

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.4118. Min Act: -0.0000

Data Index: 1490750 (Python Code)

Max Activating Token Index: 682

Text #15

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.3932. Min Act: -0.0000

Data Index: 68047 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.4068. Min Act: -0.0000

Data Index: 1564830 (Python Code)

Max Activating Token Index: 657

Text #17

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.3984. Min Act: -0.0000

Data Index: 1290175 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.4337. Min Act: -0.0000

Data Index: 1546142 (Python Code)

Max Activating Token Index: 579

Text #19

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.3409. Min Act: -0.0000

Data Index: 1234853 (C4 (Web Text))

Max Activating Token Index: 187