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

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

Neuron 3167 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: 0.1440. Min Range: -0.1440

Max Act: 0.1303. Min Act: -0.0000

Data Index: 1087609 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1440. Min Act: -0.0000

Data Index: 938434 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1331. Min Act: -0.0000

Data Index: 277179 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1290. Min Act: -0.0000

Data Index: 35223 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1246. Min Act: -0.0000

Data Index: 312523 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1126. Min Act: -0.0000

Data Index: 1023762 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1130. Min Act: -0.0000

Data Index: 697740 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1113. Min Act: -0.0000

Data Index: 264290 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1107. Min Act: -0.0000

Data Index: 58797 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1116. Min Act: -0.0000

Data Index: 628261 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1063. Min Act: -0.0000

Data Index: 1248350 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1056. Min Act: -0.0000

Data Index: 531878 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1084. Min Act: -0.0000

Data Index: 1429080 (Python Code)

Max Activating Token Index: 1019

Text #13

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1123. Min Act: -0.0000

Data Index: 348618 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1005. Min Act: -0.0000

Data Index: 429689 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1035. Min Act: -0.0000

Data Index: 430729 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1109. Min Act: -0.0000

Data Index: 443772 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1067. Min Act: -0.0000

Data Index: 1553011 (Python Code)

Max Activating Token Index: 660

Text #18

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1116. Min Act: -0.0000

Data Index: 984632 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1076. Min Act: -0.0000

Data Index: 650522 (C4 (Web Text))

Max Activating Token Index: 52