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

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

Neuron 2650 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1283. Min Act: -0.0000

Data Index: 1631621 (Python Code)

Max Activating Token Index: 919

Text #1

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1220. Min Act: -0.0000

Data Index: 656976 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1200. Min Act: -0.0000

Data Index: 1045890 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1231. Min Act: -0.0000

Data Index: 1576014 (Python Code)

Max Activating Token Index: 1021

Text #4

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1141. Min Act: -0.0000

Data Index: 429704 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1166. Min Act: -0.0000

Data Index: 482966 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1192. Min Act: -0.0000

Data Index: 1520538 (Python Code)

Max Activating Token Index: 1007

Text #7

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1040. Min Act: -0.0000

Data Index: 426761 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1137. Min Act: -0.0000

Data Index: 1444256 (Python Code)

Max Activating Token Index: 499

Text #9

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1146. Min Act: -0.0000

Data Index: 1385512 (Python Code)

Max Activating Token Index: 396

Text #10

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1390407 (Python Code)

Max Activating Token Index: 945

Text #11

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1002. Min Act: -0.0000

Data Index: 812580 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1108. Min Act: -0.0000

Data Index: 1639184 (Python Code)

Max Activating Token Index: 647

Text #13

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1044. Min Act: -0.0000

Data Index: 1460632 (Python Code)

Max Activating Token Index: 556

Text #14

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1029. Min Act: -0.0000

Data Index: 1627967 (Python Code)

Max Activating Token Index: 749

Text #15

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1164. Min Act: -0.0000

Data Index: 1401023 (Python Code)

Max Activating Token Index: 681

Text #16

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0984. Min Act: -0.0000

Data Index: 530071 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1594671 (Python Code)

Max Activating Token Index: 900

Text #18

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1071. Min Act: -0.0000

Data Index: 1371869 (Python Code)

Max Activating Token Index: 405

Text #19

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0937. Min Act: -0.0001

Data Index: 233085 (C4 (Web Text))

Max Activating Token Index: 199