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

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

Neuron 2979 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.9119. Min Act: 0.0001

Data Index: 1422337 (Python Code)

Max Activating Token Index: 680

Text #1

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.9224. Min Act: -0.0000

Data Index: 1494944 (Python Code)

Max Activating Token Index: 325

Text #2

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1460454 (Python Code)

Max Activating Token Index: 316

Text #3

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.8246. Min Act: -0.0000

Data Index: 1564448 (Python Code)

Max Activating Token Index: 792

Text #4

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.7899. Min Act: 0.0001

Data Index: 1440427 (Python Code)

Max Activating Token Index: 18

Text #5

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.7331. Min Act: -0.0000

Data Index: 1637767 (Python Code)

Max Activating Token Index: 236

Text #6

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.7281. Min Act: -0.0000

Data Index: 1583438 (Python Code)

Max Activating Token Index: 71

Text #7

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.7175. Min Act: 0.0001

Data Index: 1403327 (Python Code)

Max Activating Token Index: 199

Text #8

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1418508 (Python Code)

Max Activating Token Index: 977

Text #9

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.6888. Min Act: 0.0002

Data Index: 1459731 (Python Code)

Max Activating Token Index: 282

Text #10

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.6419. Min Act: 0.0001

Data Index: 1638152 (Python Code)

Max Activating Token Index: 170

Text #11

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.6625. Min Act: 0.0001

Data Index: 1407914 (Python Code)

Max Activating Token Index: 67

Text #12

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.6686. Min Act: 0.0002

Data Index: 1431898 (Python Code)

Max Activating Token Index: 657

Text #13

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.6526. Min Act: -0.0000

Data Index: 1406921 (Python Code)

Max Activating Token Index: 104

Text #14

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.6515. Min Act: 0.0001

Data Index: 1467047 (Python Code)

Max Activating Token Index: 755

Text #15

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.6160. Min Act: 0.0001

Data Index: 1361671 (Python Code)

Max Activating Token Index: 108

Text #16

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.6073. Min Act: 0.0002

Data Index: 1601718 (Python Code)

Max Activating Token Index: 713

Text #17

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.6056. Min Act: -0.0000

Data Index: 1454132 (Python Code)

Max Activating Token Index: 476

Text #18

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1532055 (Python Code)

Max Activating Token Index: 172

Text #19

Max Range: 0.9224. Min Range: -0.9224

Max Act: 0.6034. Min Act: -0.0000

Data Index: 1450112 (Python Code)

Max Activating Token Index: 559