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

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

Neuron 2333 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5478. Min Range: -2.5478

Max Act: 2.5478. Min Act: -0.0000

Data Index: 1618482 (Python Code)

Max Activating Token Index: 16

Text #1

Max Range: 2.5478. Min Range: -2.5478

Max Act: 1.9645. Min Act: -0.0000

Data Index: 1470463 (Python Code)

Max Activating Token Index: 305

Text #2

Max Range: 2.5478. Min Range: -2.5478

Max Act: 1.9702. Min Act: -0.0000

Data Index: 1542341 (Python Code)

Max Activating Token Index: 61

Text #3

Max Range: 2.5478. Min Range: -2.5478

Max Act: 1.8485. Min Act: -0.0000

Data Index: 1376267 (Python Code)

Max Activating Token Index: 409

Text #4

Max Range: 2.5478. Min Range: -2.5478

Max Act: 1.7817. Min Act: -0.0000

Data Index: 707045 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 2.5478. Min Range: -2.5478

Max Act: 1.8648. Min Act: -0.0000

Data Index: 700919 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 2.5478. Min Range: -2.5478

Max Act: 1.9474. Min Act: -0.0000

Data Index: 1459972 (Python Code)

Max Activating Token Index: 202

Text #7

Max Range: 2.5478. Min Range: -2.5478

Max Act: 1.7087. Min Act: -0.0000

Data Index: 1487593 (Python Code)

Max Activating Token Index: 107

Text #8

Max Range: 2.5478. Min Range: -2.5478

Max Act: 1.9599. Min Act: -0.0000

Data Index: 1544175 (Python Code)

Max Activating Token Index: 787

Text #9

Max Range: 2.5478. Min Range: -2.5478

Max Act: 1.7482. Min Act: -0.0000

Data Index: 959284 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 2.5478. Min Range: -2.5478

Max Act: 1.7118. Min Act: -0.0000

Data Index: 1612062 (Python Code)

Max Activating Token Index: 22

Text #11

Max Range: 2.5478. Min Range: -2.5478

Max Act: 1.5860. Min Act: -0.0000

Data Index: 1546399 (Python Code)

Max Activating Token Index: 957

Text #12

Max Range: 2.5478. Min Range: -2.5478

Max Act: 1.6455. Min Act: -0.0000

Data Index: 1596035 (Python Code)

Max Activating Token Index: 715

Text #13

Max Range: 2.5478. Min Range: -2.5478

Max Act: 1.5534. Min Act: -0.0000

Data Index: 1017362 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 2.5478. Min Range: -2.5478

Max Act: 1.7286. Min Act: -0.0000

Data Index: 1634696 (Python Code)

Max Activating Token Index: 1002

Text #15

Max Range: 2.5478. Min Range: -2.5478

Max Act: 1.7261. Min Act: -0.0000

Data Index: 1635834 (Python Code)

Max Activating Token Index: 14

Text #16

Max Range: 2.5478. Min Range: -2.5478

Max Act: 1.6109. Min Act: -0.0000

Data Index: 1553106 (Python Code)

Max Activating Token Index: 669

Text #17

Max Range: 2.5478. Min Range: -2.5478

Max Act: 1.5047. Min Act: -0.0000

Data Index: 1544905 (Python Code)

Max Activating Token Index: 642

Text #18

Max Range: 2.5478. Min Range: -2.5478

Max Act: 1.5959. Min Act: -0.0000

Data Index: 1411147 (Python Code)

Max Activating Token Index: 90

Text #19

Max Range: 2.5478. Min Range: -2.5478

Max Act: 1.5762. Min Act: -0.0000

Data Index: 1452072 (Python Code)

Max Activating Token Index: 847