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

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

Neuron 5088 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.9727. Min Act: -0.0000

Data Index: 275716 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 1.0756. Min Range: -1.0756

Max Act: 1.0756. Min Act: -0.0000

Data Index: 282150 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.9249. Min Act: -0.0000

Data Index: 1291735 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.9245. Min Act: -0.0000

Data Index: 1079428 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.8690. Min Act: -0.0000

Data Index: 1196112 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.8257. Min Act: -0.0000

Data Index: 249917 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.8183. Min Act: -0.0000

Data Index: 209744 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.7496. Min Act: -0.0000

Data Index: 711400 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.7359. Min Act: -0.0000

Data Index: 1166119 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.5962. Min Act: -0.0000

Data Index: 324504 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1082932 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.4920. Min Act: -0.0000

Data Index: 68573 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.5000. Min Act: -0.0000

Data Index: 1214560 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.5257. Min Act: -0.0000

Data Index: 912681 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.4593. Min Act: -0.0000

Data Index: 938013 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.4064. Min Act: -0.0000

Data Index: 919217 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.4007. Min Act: -0.0000

Data Index: 478630 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1040890 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.4405. Min Act: -0.0000

Data Index: 3686 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.4368. Min Act: -0.0000

Data Index: 923788 (C4 (Web Text))

Max Activating Token Index: 699