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

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

Neuron 3845 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1523. Min Range: -2.1523

Max Act: 2.1523. Min Act: -0.0000

Data Index: 1558574 (Python Code)

Max Activating Token Index: 493

Text #1

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.5473. Min Act: -0.0000

Data Index: 1650636 (Python Code)

Max Activating Token Index: 585

Text #2

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.5848. Min Act: -0.0000

Data Index: 1652898 (Python Code)

Max Activating Token Index: 503

Text #3

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.5780. Min Act: -0.0001

Data Index: 1596946 (Python Code)

Max Activating Token Index: 890

Text #4

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.5422. Min Act: -0.0000

Data Index: 1491693 (Python Code)

Max Activating Token Index: 986

Text #5

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.5692. Min Act: -0.0000

Data Index: 1366768 (Python Code)

Max Activating Token Index: 37

Text #6

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.5043. Min Act: -0.0000

Data Index: 1630380 (Python Code)

Max Activating Token Index: 647

Text #7

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.5960. Min Act: -0.0000

Data Index: 1540751 (Python Code)

Max Activating Token Index: 693

Text #8

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.5430. Min Act: -0.0000

Data Index: 1412747 (Python Code)

Max Activating Token Index: 24

Text #9

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.4797. Min Act: -0.0001

Data Index: 1384544 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.4803. Min Act: -0.0001

Data Index: 1536098 (Python Code)

Max Activating Token Index: 17

Text #11

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.5030. Min Act: -0.0000

Data Index: 1395335 (Python Code)

Max Activating Token Index: 549

Text #12

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.4449. Min Act: -0.0001

Data Index: 1565656 (Python Code)

Max Activating Token Index: 19

Text #13

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.4074. Min Act: -0.0001

Data Index: 1634407 (Python Code)

Max Activating Token Index: 178

Text #14

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.4303. Min Act: -0.0000

Data Index: 1490966 (Python Code)

Max Activating Token Index: 20

Text #15

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.4010. Min Act: -0.0000

Data Index: 1503176 (Python Code)

Max Activating Token Index: 111

Text #16

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.4469. Min Act: -0.0001

Data Index: 1368321 (Python Code)

Max Activating Token Index: 58

Text #17

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.4449. Min Act: -0.0001

Data Index: 1496906 (Python Code)

Max Activating Token Index: 962

Text #18

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.3825. Min Act: -0.0001

Data Index: 1460742 (Python Code)

Max Activating Token Index: 14

Text #19

Max Range: 2.1523. Min Range: -2.1523

Max Act: 1.3586. Min Act: -0.0001

Data Index: 1653460 (Python Code)

Max Activating Token Index: 871