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

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

Neuron 4917 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0970. Min Range: -1.0970

Max Act: 1.0479. Min Act: -0.0001

Data Index: 1601910 (Python Code)

Max Activating Token Index: 145

Text #1

Max Range: 1.0970. Min Range: -1.0970

Max Act: 1.0351. Min Act: -0.0001

Data Index: 1486657 (Python Code)

Max Activating Token Index: 50

Text #2

Max Range: 1.0970. Min Range: -1.0970

Max Act: 1.0970. Min Act: -0.0001

Data Index: 1599605 (Python Code)

Max Activating Token Index: 377

Text #3

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.9828. Min Act: -0.0001

Data Index: 1525167 (Python Code)

Max Activating Token Index: 141

Text #4

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.9848. Min Act: -0.0001

Data Index: 1522882 (Python Code)

Max Activating Token Index: 27

Text #5

Max Range: 1.0970. Min Range: -1.0970

Max Act: 1.0110. Min Act: -0.0000

Data Index: 1399189 (Python Code)

Max Activating Token Index: 174

Text #6

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1553394 (Python Code)

Max Activating Token Index: 47

Text #7

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.9378. Min Act: -0.0000

Data Index: 1387381 (Python Code)

Max Activating Token Index: 130

Text #8

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.9572. Min Act: -0.0001

Data Index: 1485551 (Python Code)

Max Activating Token Index: 427

Text #9

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.9266. Min Act: -0.0000

Data Index: 1494557 (Python Code)

Max Activating Token Index: 312

Text #10

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.9540. Min Act: -0.0000

Data Index: 1463774 (Python Code)

Max Activating Token Index: 174

Text #11

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.9815. Min Act: -0.0001

Data Index: 1624277 (Python Code)

Max Activating Token Index: 122

Text #12

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.8212. Min Act: -0.0000

Data Index: 1523214 (Python Code)

Max Activating Token Index: 745

Text #13

Max Range: 1.0970. Min Range: -1.0970

Max Act: 1.0105. Min Act: -0.0001

Data Index: 1564855 (Python Code)

Max Activating Token Index: 31

Text #14

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.9451. Min Act: -0.0001

Data Index: 1554881 (Python Code)

Max Activating Token Index: 35

Text #15

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.9757. Min Act: -0.0001

Data Index: 1543365 (Python Code)

Max Activating Token Index: 764

Text #16

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.9430. Min Act: -0.0001

Data Index: 1592421 (Python Code)

Max Activating Token Index: 437

Text #17

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.8775. Min Act: -0.0000

Data Index: 1635199 (Python Code)

Max Activating Token Index: 311

Text #18

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.9069. Min Act: -0.0000

Data Index: 1510807 (Python Code)

Max Activating Token Index: 489

Text #19

Max Range: 1.0970. Min Range: -1.0970

Max Act: 0.9271. Min Act: -0.0001

Data Index: 1654221 (Python Code)

Max Activating Token Index: 835