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

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

Neuron 5396 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7775. Min Range: -3.7775

Max Act: 3.7775. Min Act: -0.0000

Data Index: 1402140 (Python Code)

Max Activating Token Index: 996

Text #1

Max Range: 3.7775. Min Range: -3.7775

Max Act: 3.3962. Min Act: -0.0000

Data Index: 1491671 (Python Code)

Max Activating Token Index: 968

Text #2

Max Range: 3.7775. Min Range: -3.7775

Max Act: 3.3898. Min Act: -0.0000

Data Index: 1538585 (Python Code)

Max Activating Token Index: 592

Text #3

Max Range: 3.7775. Min Range: -3.7775

Max Act: 3.5984. Min Act: -0.0000

Data Index: 1650783 (Python Code)

Max Activating Token Index: 917

Text #4

Max Range: 3.7775. Min Range: -3.7775

Max Act: 3.4695. Min Act: -0.0000

Data Index: 1522262 (Python Code)

Max Activating Token Index: 356

Text #5

Max Range: 3.7775. Min Range: -3.7775

Max Act: 3.2951. Min Act: -0.0000

Data Index: 1489248 (Python Code)

Max Activating Token Index: 380

Text #6

Max Range: 3.7775. Min Range: -3.7775

Max Act: 3.2285. Min Act: -0.0000

Data Index: 1491098 (Python Code)

Max Activating Token Index: 199

Text #7

Max Range: 3.7775. Min Range: -3.7775

Max Act: 3.1668. Min Act: -0.0000

Data Index: 1643146 (Python Code)

Max Activating Token Index: 208

Text #8

Max Range: 3.7775. Min Range: -3.7775

Max Act: 2.9693. Min Act: -0.0000

Data Index: 1405251 (Python Code)

Max Activating Token Index: 284

Text #9

Max Range: 3.7775. Min Range: -3.7775

Max Act: 3.0880. Min Act: -0.0000

Data Index: 1438558 (Python Code)

Max Activating Token Index: 899

Text #10

Max Range: 3.7775. Min Range: -3.7775

Max Act: 3.1994. Min Act: -0.0000

Data Index: 1461404 (Python Code)

Max Activating Token Index: 877

Text #11

Max Range: 3.7775. Min Range: -3.7775

Max Act: 2.8870. Min Act: -0.0000

Data Index: 1656529 (Python Code)

Max Activating Token Index: 456

Text #12

Max Range: 3.7775. Min Range: -3.7775

Max Act: 3.0144. Min Act: -0.0000

Data Index: 1555370 (Python Code)

Max Activating Token Index: 720

Text #13

Max Range: 3.7775. Min Range: -3.7775

Max Act: 3.1565. Min Act: -0.0000

Data Index: 1394759 (Python Code)

Max Activating Token Index: 238

Text #14

Max Range: 3.7775. Min Range: -3.7775

Max Act: 3.0187. Min Act: -0.0000

Data Index: 1360092 (Python Code)

Max Activating Token Index: 112

Text #15

Max Range: 3.7775. Min Range: -3.7775

Max Act: 2.9944. Min Act: -0.0000

Data Index: 1444698 (Python Code)

Max Activating Token Index: 609

Text #16

Max Range: 3.7775. Min Range: -3.7775

Max Act: 3.0110. Min Act: -0.0000

Data Index: 1549635 (Python Code)

Max Activating Token Index: 570

Text #17

Max Range: 3.7775. Min Range: -3.7775

Max Act: 3.0802. Min Act: -0.0000

Data Index: 1510112 (Python Code)

Max Activating Token Index: 54

Text #18

Max Range: 3.7775. Min Range: -3.7775

Max Act: 2.7761. Min Act: -0.0000

Data Index: 1589121 (Python Code)

Max Activating Token Index: 523

Text #19

Max Range: 3.7775. Min Range: -3.7775

Max Act: 2.8980. Min Act: -0.0000

Data Index: 1616601 (Python Code)

Max Activating Token Index: 405