Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1502 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.1511. Min Range: -5.1511

Max Act: 5.1511. Min Act: -0.0000

Data Index: 1481760 (Python Code)

Max Activating Token Index: 112

Text #1

Max Range: 5.1511. Min Range: -5.1511

Max Act: 4.1887. Min Act: -0.0000

Data Index: 1523097 (Python Code)

Max Activating Token Index: 814

Text #2

Max Range: 5.1511. Min Range: -5.1511

Max Act: 3.7759. Min Act: -0.0000

Data Index: 1632409 (Python Code)

Max Activating Token Index: 249

Text #3

Max Range: 5.1511. Min Range: -5.1511

Max Act: 3.6029. Min Act: 0.0000

Data Index: 1640046 (Python Code)

Max Activating Token Index: 721

Text #4

Max Range: 5.1511. Min Range: -5.1511

Max Act: 3.3604. Min Act: -0.0000

Data Index: 1488187 (Python Code)

Max Activating Token Index: 928

Text #5

Max Range: 5.1511. Min Range: -5.1511

Max Act: 3.5356. Min Act: -0.0000

Data Index: 1636827 (Python Code)

Max Activating Token Index: 874

Text #6

Max Range: 5.1511. Min Range: -5.1511

Max Act: 3.5952. Min Act: -0.0000

Data Index: 1409096 (Python Code)

Max Activating Token Index: 41

Text #7

Max Range: 5.1511. Min Range: -5.1511

Max Act: 3.4051. Min Act: -0.0000

Data Index: 1592994 (Python Code)

Max Activating Token Index: 36

Text #8

Max Range: 5.1511. Min Range: -5.1511

Max Act: 3.4225. Min Act: 0.0000

Data Index: 1536640 (Python Code)

Max Activating Token Index: 804

Text #9

Max Range: 5.1511. Min Range: -5.1511

Max Act: 3.5750. Min Act: -0.0000

Data Index: 1533429 (Python Code)

Max Activating Token Index: 146

Text #10

Max Range: 5.1511. Min Range: -5.1511

Max Act: 3.4091. Min Act: -0.0000

Data Index: 1418122 (Python Code)

Max Activating Token Index: 226

Text #11

Max Range: 5.1511. Min Range: -5.1511

Max Act: 3.3996. Min Act: -0.0000

Data Index: 1405204 (Python Code)

Max Activating Token Index: 27

Text #12

Max Range: 5.1511. Min Range: -5.1511

Max Act: 3.3932. Min Act: -0.0000

Data Index: 1374970 (Python Code)

Max Activating Token Index: 326

Text #13

Max Range: 5.1511. Min Range: -5.1511

Max Act: 3.3227. Min Act: -0.0000

Data Index: 1411014 (Python Code)

Max Activating Token Index: 974

Text #14

Max Range: 5.1511. Min Range: -5.1511

Max Act: 3.2953. Min Act: -0.0000

Data Index: 1576011 (Python Code)

Max Activating Token Index: 54

Text #15

Max Range: 5.1511. Min Range: -5.1511

Max Act: 3.1189. Min Act: -0.0000

Data Index: 1517764 (Python Code)

Max Activating Token Index: 559

Text #16

Max Range: 5.1511. Min Range: -5.1511

Max Act: 3.1286. Min Act: -0.0000

Data Index: 1567003 (Python Code)

Max Activating Token Index: 283

Text #17

Max Range: 5.1511. Min Range: -5.1511

Max Act: 3.2355. Min Act: -0.0000

Data Index: 1584856 (Python Code)

Max Activating Token Index: 556

Text #18

Max Range: 5.1511. Min Range: -5.1511

Max Act: 3.3436. Min Act: -0.0000

Data Index: 1375147 (Python Code)

Max Activating Token Index: 717

Text #19

Max Range: 5.1511. Min Range: -5.1511

Max Act: 3.0092. Min Act: -0.0000

Data Index: 1453496 (Python Code)

Max Activating Token Index: 180