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

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

Neuron 1969 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: 7.8047. Min Range: -7.8047

Max Act: 7.8047. Min Act: -0.0001

Data Index: 1558292 (Python Code)

Max Activating Token Index: 75

Text #1

Max Range: 7.8047. Min Range: -7.8047

Max Act: 7.7583. Min Act: -0.0001

Data Index: 1519211 (Python Code)

Max Activating Token Index: 833

Text #2

Max Range: 7.8047. Min Range: -7.8047

Max Act: 7.4449. Min Act: -0.0001

Data Index: 1618793 (Python Code)

Max Activating Token Index: 181

Text #3

Max Range: 7.8047. Min Range: -7.8047

Max Act: 7.1794. Min Act: -0.0000

Data Index: 1526547 (Python Code)

Max Activating Token Index: 907

Text #4

Max Range: 7.8047. Min Range: -7.8047

Max Act: 7.0748. Min Act: -0.0001

Data Index: 1421426 (Python Code)

Max Activating Token Index: 175

Text #5

Max Range: 7.8047. Min Range: -7.8047

Max Act: 7.0425. Min Act: -0.0001

Data Index: 1507208 (Python Code)

Max Activating Token Index: 779

Text #6

Max Range: 7.8047. Min Range: -7.8047

Max Act: 7.2229. Min Act: -0.0001

Data Index: 1512070 (Python Code)

Max Activating Token Index: 263

Text #7

Max Range: 7.8047. Min Range: -7.8047

Max Act: 6.7832. Min Act: -0.0001

Data Index: 1575544 (Python Code)

Max Activating Token Index: 246

Text #8

Max Range: 7.8047. Min Range: -7.8047

Max Act: 6.9065. Min Act: -0.0001

Data Index: 1586082 (Python Code)

Max Activating Token Index: 174

Text #9

Max Range: 7.8047. Min Range: -7.8047

Max Act: 7.0468. Min Act: -0.0001

Data Index: 1540098 (Python Code)

Max Activating Token Index: 419

Text #10

Max Range: 7.8047. Min Range: -7.8047

Max Act: 6.8261. Min Act: -0.0001

Data Index: 1484678 (Python Code)

Max Activating Token Index: 624

Text #11

Max Range: 7.8047. Min Range: -7.8047

Max Act: 6.7983. Min Act: -0.0001

Data Index: 1456127 (Python Code)

Max Activating Token Index: 796

Text #12

Max Range: 7.8047. Min Range: -7.8047

Max Act: 6.9461. Min Act: -0.0001

Data Index: 1361455 (Python Code)

Max Activating Token Index: 911

Text #13

Max Range: 7.8047. Min Range: -7.8047

Max Act: 6.7591. Min Act: -0.0001

Data Index: 1635147 (Python Code)

Max Activating Token Index: 575

Text #14

Max Range: 7.8047. Min Range: -7.8047

Max Act: 6.5381. Min Act: -0.0001

Data Index: 1640283 (Python Code)

Max Activating Token Index: 639

Text #15

Max Range: 7.8047. Min Range: -7.8047

Max Act: 6.8683. Min Act: -0.0001

Data Index: 1481121 (Python Code)

Max Activating Token Index: 536

Text #16

Max Range: 7.8047. Min Range: -7.8047

Max Act: 6.7032. Min Act: -0.0001

Data Index: 1493559 (Python Code)

Max Activating Token Index: 182

Text #17

Max Range: 7.8047. Min Range: -7.8047

Max Act: 6.8685. Min Act: -0.0001

Data Index: 1614676 (Python Code)

Max Activating Token Index: 741

Text #18

Max Range: 7.8047. Min Range: -7.8047

Max Act: 6.1113. Min Act: -0.0001

Data Index: 1647147 (Python Code)

Max Activating Token Index: 617

Text #19

Max Range: 7.8047. Min Range: -7.8047

Max Act: 6.4884. Min Act: -0.0001

Data Index: 1632850 (Python Code)

Max Activating Token Index: 582