Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1505 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1742. Min Act: -0.0000

Data Index: 1085423 (The Pile)

Max Activating Token Index: 197

Text #1

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1408. Min Act: -0.0000

Data Index: 1955296 (The Pile)

Max Activating Token Index: 785

Text #2

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1334304 (The Pile)

Max Activating Token Index: 876

Text #3

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1207. Min Act: -0.0000

Data Index: 623164 (The Pile)

Max Activating Token Index: 184

Text #4

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1060. Min Act: -0.0000

Data Index: 1197532 (The Pile)

Max Activating Token Index: 780

Text #5

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1229. Min Act: -0.0000

Data Index: 1807901 (The Pile)

Max Activating Token Index: 630

Text #6

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1117. Min Act: -0.0000

Data Index: 112396 (The Pile)

Max Activating Token Index: 490

Text #7

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1028. Min Act: -0.0000

Data Index: 972634 (The Pile)

Max Activating Token Index: 588

Text #8

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1046. Min Act: -0.0000

Data Index: 740195 (The Pile)

Max Activating Token Index: 174

Text #9

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1001. Min Act: -0.0000

Data Index: 1090795 (The Pile)

Max Activating Token Index: 63

Text #10

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1046. Min Act: -0.0000

Data Index: 1418677 (The Pile)

Max Activating Token Index: 307

Text #11

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1047. Min Act: -0.0000

Data Index: 1748296 (The Pile)

Max Activating Token Index: 22

Text #12

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1000. Min Act: -0.0000

Data Index: 1193171 (The Pile)

Max Activating Token Index: 75

Text #13

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.0990. Min Act: -0.0000

Data Index: 1266504 (The Pile)

Max Activating Token Index: 796

Text #14

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.0981. Min Act: -0.0000

Data Index: 889137 (The Pile)

Max Activating Token Index: 314

Text #15

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1015. Min Act: -0.0000

Data Index: 1482711 (The Pile)

Max Activating Token Index: 290

Text #16

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1145252 (The Pile)

Max Activating Token Index: 805

Text #17

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.0934. Min Act: -0.0000

Data Index: 1101085 (The Pile)

Max Activating Token Index: 182

Text #18

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.0870. Min Act: -0.0000

Data Index: 68674 (The Pile)

Max Activating Token Index: 566

Text #19

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.0890. Min Act: -0.0000

Data Index: 647320 (The Pile)

Max Activating Token Index: 801