Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1937 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2137. Min Range: -1.2137

Max Act: 1.2137. Min Act: -0.0001

Data Index: 1532276 (Python Code)

Max Activating Token Index: 891

Text #1

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.9619. Min Act: -0.0001

Data Index: 1496059 (Python Code)

Max Activating Token Index: 177

Text #2

Max Range: 1.2137. Min Range: -1.2137

Max Act: 1.1850. Min Act: -0.0001

Data Index: 1432949 (Python Code)

Max Activating Token Index: 303

Text #3

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.9974. Min Act: -0.0001

Data Index: 1561576 (Python Code)

Max Activating Token Index: 958

Text #4

Max Range: 1.2137. Min Range: -1.2137

Max Act: 1.0288. Min Act: -0.0001

Data Index: 1641200 (Python Code)

Max Activating Token Index: 381

Text #5

Max Range: 1.2137. Min Range: -1.2137

Max Act: 1.0139. Min Act: -0.0001

Data Index: 1598138 (Python Code)

Max Activating Token Index: 645

Text #6

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.9767. Min Act: -0.0001

Data Index: 1554992 (Python Code)

Max Activating Token Index: 186

Text #7

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.9912. Min Act: -0.0001

Data Index: 1396146 (Python Code)

Max Activating Token Index: 174

Text #8

Max Range: 1.2137. Min Range: -1.2137

Max Act: 1.0082. Min Act: -0.0001

Data Index: 1521311 (Python Code)

Max Activating Token Index: 446

Text #9

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.9574. Min Act: -0.0001

Data Index: 1552862 (Python Code)

Max Activating Token Index: 112

Text #10

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.9022. Min Act: -0.0001

Data Index: 1416403 (Python Code)

Max Activating Token Index: 597

Text #11

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.8705. Min Act: -0.0001

Data Index: 1531441 (Python Code)

Max Activating Token Index: 290

Text #12

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.8576. Min Act: -0.0001

Data Index: 1587890 (Python Code)

Max Activating Token Index: 501

Text #13

Max Range: 1.2137. Min Range: -1.2137

Max Act: 1.0029. Min Act: -0.0001

Data Index: 1359977 (Python Code)

Max Activating Token Index: 673

Text #14

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.9384. Min Act: -0.0001

Data Index: 1652058 (Python Code)

Max Activating Token Index: 992

Text #15

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.9351. Min Act: -0.0001

Data Index: 1412065 (Python Code)

Max Activating Token Index: 240

Text #16

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.7615. Min Act: -0.0001

Data Index: 1442575 (Python Code)

Max Activating Token Index: 605

Text #17

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.8254. Min Act: -0.0001

Data Index: 1374640 (Python Code)

Max Activating Token Index: 59

Text #18

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.6631. Min Act: -0.0001

Data Index: 1646018 (Python Code)

Max Activating Token Index: 831

Text #19

Max Range: 1.2137. Min Range: -1.2137

Max Act: 0.8192. Min Act: -0.0001

Data Index: 1406238 (Python Code)

Max Activating Token Index: 115