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

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

Neuron 39 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.6031. Min Range: -2.6031

Max Act: 2.4945. Min Act: -0.0000

Data Index: 1558540 (Python Code)

Max Activating Token Index: 901

Text #1

Max Range: 2.6031. Min Range: -2.6031

Max Act: 2.6031. Min Act: -0.0000

Data Index: 1525044 (Python Code)

Max Activating Token Index: 137

Text #2

Max Range: 2.6031. Min Range: -2.6031

Max Act: 2.2581. Min Act: -0.0000

Data Index: 1473778 (Python Code)

Max Activating Token Index: 930

Text #3

Max Range: 2.6031. Min Range: -2.6031

Max Act: 2.0969. Min Act: -0.0000

Data Index: 1456339 (Python Code)

Max Activating Token Index: 957

Text #4

Max Range: 2.6031. Min Range: -2.6031

Max Act: 2.3476. Min Act: -0.0000

Data Index: 1456999 (Python Code)

Max Activating Token Index: 901

Text #5

Max Range: 2.6031. Min Range: -2.6031

Max Act: 2.4000. Min Act: -0.0000

Data Index: 1656224 (Python Code)

Max Activating Token Index: 333

Text #6

Max Range: 2.6031. Min Range: -2.6031

Max Act: 2.3746. Min Act: -0.0000

Data Index: 1638506 (Python Code)

Max Activating Token Index: 38

Text #7

Max Range: 2.6031. Min Range: -2.6031

Max Act: 2.2933. Min Act: -0.0000

Data Index: 1464626 (Python Code)

Max Activating Token Index: 51

Text #8

Max Range: 2.6031. Min Range: -2.6031

Max Act: 2.2148. Min Act: -0.0000

Data Index: 1363062 (Python Code)

Max Activating Token Index: 92

Text #9

Max Range: 2.6031. Min Range: -2.6031

Max Act: 2.2629. Min Act: -0.0000

Data Index: 1463857 (Python Code)

Max Activating Token Index: 62

Text #10

Max Range: 2.6031. Min Range: -2.6031

Max Act: 2.2552. Min Act: -0.0000

Data Index: 1405207 (Python Code)

Max Activating Token Index: 124

Text #11

Max Range: 2.6031. Min Range: -2.6031

Max Act: 2.0994. Min Act: -0.0000

Data Index: 1402055 (Python Code)

Max Activating Token Index: 62

Text #12

Max Range: 2.6031. Min Range: -2.6031

Max Act: 2.2759. Min Act: -0.0000

Data Index: 1616078 (Python Code)

Max Activating Token Index: 20

Text #13

Max Range: 2.6031. Min Range: -2.6031

Max Act: 2.2609. Min Act: -0.0000

Data Index: 1599844 (Python Code)

Max Activating Token Index: 134

Text #14

Max Range: 2.6031. Min Range: -2.6031

Max Act: 2.0540. Min Act: -0.0000

Data Index: 1626806 (Python Code)

Max Activating Token Index: 14

Text #15

Max Range: 2.6031. Min Range: -2.6031

Max Act: 2.0540. Min Act: -0.0000

Data Index: 1506195 (Python Code)

Max Activating Token Index: 14

Text #16

Max Range: 2.6031. Min Range: -2.6031

Max Act: 1.9756. Min Act: -0.0000

Data Index: 1613163 (Python Code)

Max Activating Token Index: 32

Text #17

Max Range: 2.6031. Min Range: -2.6031

Max Act: 1.9515. Min Act: -0.0000

Data Index: 1461288 (Python Code)

Max Activating Token Index: 433

Text #18

Max Range: 2.6031. Min Range: -2.6031

Max Act: 1.9594. Min Act: -0.0000

Data Index: 1409371 (Python Code)

Max Activating Token Index: 695

Text #19

Max Range: 2.6031. Min Range: -2.6031

Max Act: 2.0414. Min Act: -0.0000

Data Index: 1427071 (Python Code)

Max Activating Token Index: 824