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

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

Neuron 1123 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1050. Min Range: -1.1050

Max Act: 1.1050. Min Act: -0.0000

Data Index: 546772 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 1.1050. Min Range: -1.1050

Max Act: 1.0515. Min Act: -0.0000

Data Index: 693542 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 1.1050. Min Range: -1.1050

Max Act: 1.0860. Min Act: -0.0000

Data Index: 596825 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 1.1050. Min Range: -1.1050

Max Act: 0.9973. Min Act: -0.0000

Data Index: 445498 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 1.1050. Min Range: -1.1050

Max Act: 1.0228. Min Act: -0.0000

Data Index: 131680 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 1.1050. Min Range: -1.1050

Max Act: 0.9645. Min Act: -0.0000

Data Index: 712425 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 1.1050. Min Range: -1.1050

Max Act: 0.9554. Min Act: -0.0000

Data Index: 480683 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 1.1050. Min Range: -1.1050

Max Act: 0.9245. Min Act: -0.0000

Data Index: 37399 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 1.1050. Min Range: -1.1050

Max Act: 0.8753. Min Act: -0.0000

Data Index: 627087 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 1.1050. Min Range: -1.1050

Max Act: 0.8692. Min Act: -0.0000

Data Index: 246114 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 1.1050. Min Range: -1.1050

Max Act: 0.8692. Min Act: -0.0000

Data Index: 226918 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 1.1050. Min Range: -1.1050

Max Act: 0.8663. Min Act: -0.0000

Data Index: 1212047 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 1.1050. Min Range: -1.1050

Max Act: 0.8891. Min Act: -0.0000

Data Index: 347301 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 1.1050. Min Range: -1.1050

Max Act: 0.9224. Min Act: -0.0000

Data Index: 921676 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 1.1050. Min Range: -1.1050

Max Act: 0.9085. Min Act: -0.0000

Data Index: 868956 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 1.1050. Min Range: -1.1050

Max Act: 0.8653. Min Act: -0.0000

Data Index: 1356013 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 1.1050. Min Range: -1.1050

Max Act: 0.8483. Min Act: -0.0000

Data Index: 645518 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 1.1050. Min Range: -1.1050

Max Act: 0.8638. Min Act: -0.0000

Data Index: 619232 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 1.1050. Min Range: -1.1050

Max Act: 0.8904. Min Act: -0.0000

Data Index: 1334897 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 1.1050. Min Range: -1.1050

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1176164 (C4 (Web Text))

Max Activating Token Index: 286