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

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

Neuron 2063 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: 0.5820. Min Range: -0.5820

Max Act: 0.5731. Min Act: -0.0000

Data Index: 1466877 (Python Code)

Max Activating Token Index: 86

Text #1

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.5761. Min Act: -0.0001

Data Index: 1602286 (Python Code)

Max Activating Token Index: 1003

Text #2

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.5820. Min Act: -0.0000

Data Index: 1588019 (Python Code)

Max Activating Token Index: 205

Text #3

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.5435. Min Act: -0.0001

Data Index: 1546793 (Python Code)

Max Activating Token Index: 79

Text #4

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.5032. Min Act: -0.0000

Data Index: 1608737 (Python Code)

Max Activating Token Index: 784

Text #5

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1647223 (Python Code)

Max Activating Token Index: 603

Text #6

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.5473. Min Act: -0.0001

Data Index: 1576615 (Python Code)

Max Activating Token Index: 349

Text #7

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.5197. Min Act: -0.0001

Data Index: 1532516 (Python Code)

Max Activating Token Index: 456

Text #8

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.5175. Min Act: -0.0001

Data Index: 1581080 (Python Code)

Max Activating Token Index: 525

Text #9

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.5037. Min Act: -0.0001

Data Index: 1495443 (Python Code)

Max Activating Token Index: 132

Text #10

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1608945 (Python Code)

Max Activating Token Index: 123

Text #11

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.5190. Min Act: -0.0001

Data Index: 1392791 (Python Code)

Max Activating Token Index: 298

Text #12

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4833. Min Act: -0.0001

Data Index: 1363304 (Python Code)

Max Activating Token Index: 79

Text #13

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4999. Min Act: -0.0001

Data Index: 1517159 (Python Code)

Max Activating Token Index: 83

Text #14

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.5344. Min Act: -0.0000

Data Index: 1493568 (Python Code)

Max Activating Token Index: 951

Text #15

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.5122. Min Act: -0.0001

Data Index: 1433645 (Python Code)

Max Activating Token Index: 152

Text #16

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4835. Min Act: -0.0001

Data Index: 1468502 (Python Code)

Max Activating Token Index: 459

Text #17

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4985. Min Act: -0.0001

Data Index: 1366593 (Python Code)

Max Activating Token Index: 607

Text #18

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4566. Min Act: -0.0000

Data Index: 1550159 (Python Code)

Max Activating Token Index: 180

Text #19

Max Range: 0.5820. Min Range: -0.5820

Max Act: 0.4766. Min Act: -0.0001

Data Index: 1647096 (Python Code)

Max Activating Token Index: 525