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

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

Neuron 387 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: 2.3277. Min Range: -2.3277

Max Act: 2.3277. Min Act: -0.0001

Data Index: 722557 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 2.3277. Min Range: -2.3277

Max Act: 2.1542. Min Act: -0.0000

Data Index: 1514830 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 2.3277. Min Range: -2.3277

Max Act: 2.1542. Min Act: -0.0000

Data Index: 1604385 (Python Code)

Max Activating Token Index: 13

Text #3

Max Range: 2.3277. Min Range: -2.3277

Max Act: 2.1542. Min Act: -0.0000

Data Index: 1442306 (Python Code)

Max Activating Token Index: 13

Text #4

Max Range: 2.3277. Min Range: -2.3277

Max Act: 2.1542. Min Act: -0.0000

Data Index: 1528523 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 2.3277. Min Range: -2.3277

Max Act: 2.1542. Min Act: -0.0000

Data Index: 1418573 (Python Code)

Max Activating Token Index: 13

Text #6

Max Range: 2.3277. Min Range: -2.3277

Max Act: 2.1542. Min Act: -0.0000

Data Index: 1537662 (Python Code)

Max Activating Token Index: 13

Text #7

Max Range: 2.3277. Min Range: -2.3277

Max Act: 2.2162. Min Act: -0.0001

Data Index: 936052 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 2.3277. Min Range: -2.3277

Max Act: 2.0615. Min Act: -0.0001

Data Index: 1463350 (Python Code)

Max Activating Token Index: 15

Text #9

Max Range: 2.3277. Min Range: -2.3277

Max Act: 2.0615. Min Act: -0.0000

Data Index: 1574765 (Python Code)

Max Activating Token Index: 15

Text #10

Max Range: 2.3277. Min Range: -2.3277

Max Act: 1.9413. Min Act: -0.0000

Data Index: 1551778 (Python Code)

Max Activating Token Index: 12

Text #11

Max Range: 2.3277. Min Range: -2.3277

Max Act: 1.9413. Min Act: -0.0000

Data Index: 1486354 (Python Code)

Max Activating Token Index: 12

Text #12

Max Range: 2.3277. Min Range: -2.3277

Max Act: 1.9367. Min Act: -0.0001

Data Index: 1481050 (Python Code)

Max Activating Token Index: 13

Text #13

Max Range: 2.3277. Min Range: -2.3277

Max Act: 2.0995. Min Act: -0.0001

Data Index: 1362258 (Python Code)

Max Activating Token Index: 30

Text #14

Max Range: 2.3277. Min Range: -2.3277

Max Act: 2.0587. Min Act: -0.0000

Data Index: 1406960 (Python Code)

Max Activating Token Index: 14

Text #15

Max Range: 2.3277. Min Range: -2.3277

Max Act: 1.9533. Min Act: -0.0001

Data Index: 1519022 (Python Code)

Max Activating Token Index: 16

Text #16

Max Range: 2.3277. Min Range: -2.3277

Max Act: 1.9533. Min Act: -0.0000

Data Index: 1612069 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 2.3277. Min Range: -2.3277

Max Act: 2.0456. Min Act: -0.0001

Data Index: 1642608 (Python Code)

Max Activating Token Index: 230

Text #18

Max Range: 2.3277. Min Range: -2.3277

Max Act: 2.0169. Min Act: -0.0000

Data Index: 1361378 (Python Code)

Max Activating Token Index: 14

Text #19

Max Range: 2.3277. Min Range: -2.3277

Max Act: 2.0169. Min Act: -0.0001

Data Index: 1488271 (Python Code)

Max Activating Token Index: 14