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

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

Neuron 46 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.1127. Min Act: -0.0002

Data Index: 1379034 (Python Code)

Max Activating Token Index: 37

Text #1

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0934. Min Act: -0.0002

Data Index: 1128545 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0938. Min Act: -0.0002

Data Index: 220826 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0929. Min Act: -0.0002

Data Index: 928875 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0902. Min Act: -0.0002

Data Index: 1590785 (Python Code)

Max Activating Token Index: 29

Text #5

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1586852 (Python Code)

Max Activating Token Index: 4

Text #6

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0922. Min Act: -0.0002

Data Index: 1360333 (Python Code)

Max Activating Token Index: 27

Text #7

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0884. Min Act: -0.0002

Data Index: 1540293 (Python Code)

Max Activating Token Index: 11

Text #8

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0877. Min Act: -0.0002

Data Index: 1323164 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0889. Min Act: -0.0002

Data Index: 915250 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0885. Min Act: -0.0002

Data Index: 327112 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0854. Min Act: -0.0002

Data Index: 1248857 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0801. Min Act: -0.0002

Data Index: 79567 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1393469 (Python Code)

Max Activating Token Index: 134

Text #14

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0817. Min Act: -0.0002

Data Index: 1577353 (Python Code)

Max Activating Token Index: 914

Text #15

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1332633 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0793. Min Act: -0.0002

Data Index: 1060302 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1514283 (Python Code)

Max Activating Token Index: 838

Text #18

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0800. Min Act: -0.0002

Data Index: 1351017 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0782. Min Act: -0.0002

Data Index: 148465 (C4 (Web Text))

Max Activating Token Index: 626