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

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

Neuron 195 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.7122. Min Act: -0.0000

Data Index: 1392578 (Python Code)

Max Activating Token Index: 713

Text #1

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.6833. Min Act: -0.0000

Data Index: 1598711 (Python Code)

Max Activating Token Index: 823

Text #2

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.6751. Min Act: -0.0001

Data Index: 1653993 (Python Code)

Max Activating Token Index: 793

Text #3

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.7108. Min Act: -0.0000

Data Index: 1428379 (Python Code)

Max Activating Token Index: 858

Text #4

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.6287. Min Act: -0.0000

Data Index: 1636223 (Python Code)

Max Activating Token Index: 777

Text #5

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1482785 (Python Code)

Max Activating Token Index: 768

Text #6

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1446404 (Python Code)

Max Activating Token Index: 905

Text #7

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.6091. Min Act: -0.0000

Data Index: 1406875 (Python Code)

Max Activating Token Index: 561

Text #8

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5979. Min Act: -0.0000

Data Index: 1458313 (Python Code)

Max Activating Token Index: 895

Text #9

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.6373. Min Act: -0.0000

Data Index: 1471768 (Python Code)

Max Activating Token Index: 111

Text #10

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5983. Min Act: -0.0000

Data Index: 1657001 (Python Code)

Max Activating Token Index: 705

Text #11

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.6133. Min Act: -0.0000

Data Index: 1373252 (Python Code)

Max Activating Token Index: 607

Text #12

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.6499. Min Act: -0.0000

Data Index: 1467706 (Python Code)

Max Activating Token Index: 185

Text #13

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5767. Min Act: -0.0000

Data Index: 1556763 (Python Code)

Max Activating Token Index: 436

Text #14

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5649. Min Act: -0.0000

Data Index: 1485400 (Python Code)

Max Activating Token Index: 663

Text #15

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1464783 (Python Code)

Max Activating Token Index: 188

Text #16

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1536710 (Python Code)

Max Activating Token Index: 417

Text #17

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5585. Min Act: -0.0000

Data Index: 1591878 (Python Code)

Max Activating Token Index: 630

Text #18

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1460392 (Python Code)

Max Activating Token Index: 922

Text #19

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1422380 (Python Code)

Max Activating Token Index: 975