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

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

Neuron 1892 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: 1.6323. Min Range: -1.6323

Max Act: 1.6323. Min Act: -0.0000

Data Index: 1464888 (Python Code)

Max Activating Token Index: 914

Text #1

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.5638. Min Act: -0.0000

Data Index: 1379251 (Python Code)

Max Activating Token Index: 248

Text #2

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.4004. Min Act: -0.0000

Data Index: 1638816 (Python Code)

Max Activating Token Index: 389

Text #3

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.2914. Min Act: -0.0000

Data Index: 1424960 (Python Code)

Max Activating Token Index: 644

Text #4

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.4020. Min Act: -0.0000

Data Index: 1486855 (Python Code)

Max Activating Token Index: 557

Text #5

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.2060. Min Act: -0.0000

Data Index: 1459144 (Python Code)

Max Activating Token Index: 967

Text #6

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.2590. Min Act: -0.0000

Data Index: 1364595 (Python Code)

Max Activating Token Index: 477

Text #7

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.2620. Min Act: -0.0000

Data Index: 1613644 (Python Code)

Max Activating Token Index: 487

Text #8

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.2539. Min Act: -0.0000

Data Index: 1406272 (Python Code)

Max Activating Token Index: 837

Text #9

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.1561. Min Act: -0.0000

Data Index: 1470566 (Python Code)

Max Activating Token Index: 237

Text #10

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.1946. Min Act: -0.0000

Data Index: 1481973 (Python Code)

Max Activating Token Index: 938

Text #11

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.1779. Min Act: -0.0000

Data Index: 1501228 (Python Code)

Max Activating Token Index: 843

Text #12

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.1651. Min Act: -0.0000

Data Index: 1631563 (Python Code)

Max Activating Token Index: 122

Text #13

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.0876. Min Act: -0.0000

Data Index: 1645903 (Python Code)

Max Activating Token Index: 887

Text #14

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.1843. Min Act: -0.0000

Data Index: 1612629 (Python Code)

Max Activating Token Index: 671

Text #15

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.1861. Min Act: -0.0000

Data Index: 1421989 (Python Code)

Max Activating Token Index: 617

Text #16

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.1071. Min Act: -0.0000

Data Index: 1436986 (Python Code)

Max Activating Token Index: 299

Text #17

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.2026. Min Act: -0.0000

Data Index: 1365745 (Python Code)

Max Activating Token Index: 154

Text #18

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.1255. Min Act: -0.0000

Data Index: 1449240 (Python Code)

Max Activating Token Index: 201

Text #19

Max Range: 1.6323. Min Range: -1.6323

Max Act: 1.1197. Min Act: -0.0000

Data Index: 1396917 (Python Code)

Max Activating Token Index: 688