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

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

Neuron 1540 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7430. Min Range: -1.7430

Max Act: 1.7356. Min Act: -0.0001

Data Index: 1571066 (Python Code)

Max Activating Token Index: 18

Text #1

Max Range: 1.7430. Min Range: -1.7430

Max Act: 1.7430. Min Act: -0.0001

Data Index: 1420780 (Python Code)

Max Activating Token Index: 26

Text #2

Max Range: 1.7430. Min Range: -1.7430

Max Act: 1.7305. Min Act: -0.0001

Data Index: 1509153 (Python Code)

Max Activating Token Index: 781

Text #3

Max Range: 1.7430. Min Range: -1.7430

Max Act: 1.6756. Min Act: -0.0001

Data Index: 1593832 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 1.7430. Min Range: -1.7430

Max Act: 1.6187. Min Act: -0.0001

Data Index: 1633083 (Python Code)

Max Activating Token Index: 927

Text #5

Max Range: 1.7430. Min Range: -1.7430

Max Act: 1.6914. Min Act: -0.0001

Data Index: 1594292 (Python Code)

Max Activating Token Index: 25

Text #6

Max Range: 1.7430. Min Range: -1.7430

Max Act: 1.6200. Min Act: -0.0001

Data Index: 1459503 (Python Code)

Max Activating Token Index: 580

Text #7

Max Range: 1.7430. Min Range: -1.7430

Max Act: 1.6706. Min Act: -0.0001

Data Index: 1518717 (Python Code)

Max Activating Token Index: 11

Text #8

Max Range: 1.7430. Min Range: -1.7430

Max Act: 1.6722. Min Act: -0.0001

Data Index: 1462617 (Python Code)

Max Activating Token Index: 12

Text #9

Max Range: 1.7430. Min Range: -1.7430

Max Act: 1.5121. Min Act: -0.0001

Data Index: 1526053 (Python Code)

Max Activating Token Index: 829

Text #10

Max Range: 1.7430. Min Range: -1.7430

Max Act: 1.7113. Min Act: -0.0001

Data Index: 1466762 (Python Code)

Max Activating Token Index: 774

Text #11

Max Range: 1.7430. Min Range: -1.7430

Max Act: 1.6010. Min Act: -0.0001

Data Index: 1376789 (Python Code)

Max Activating Token Index: 29

Text #12

Max Range: 1.7430. Min Range: -1.7430

Max Act: 1.5455. Min Act: -0.0001

Data Index: 1532201 (Python Code)

Max Activating Token Index: 242

Text #13

Max Range: 1.7430. Min Range: -1.7430

Max Act: 1.6803. Min Act: -0.0001

Data Index: 1528926 (Python Code)

Max Activating Token Index: 18

Text #14

Max Range: 1.7430. Min Range: -1.7430

Max Act: 1.5830. Min Act: -0.0001

Data Index: 1475704 (Python Code)

Max Activating Token Index: 57

Text #15

Max Range: 1.7430. Min Range: -1.7430

Max Act: 1.6063. Min Act: -0.0001

Data Index: 1583865 (Python Code)

Max Activating Token Index: 873

Text #16

Max Range: 1.7430. Min Range: -1.7430

Max Act: 1.6126. Min Act: -0.0001

Data Index: 1627481 (Python Code)

Max Activating Token Index: 738

Text #17

Max Range: 1.7430. Min Range: -1.7430

Max Act: 1.5543. Min Act: -0.0001

Data Index: 1373433 (Python Code)

Max Activating Token Index: 40

Text #18

Max Range: 1.7430. Min Range: -1.7430

Max Act: 1.5900. Min Act: -0.0001

Data Index: 1376459 (Python Code)

Max Activating Token Index: 913

Text #19

Max Range: 1.7430. Min Range: -1.7430

Max Act: 1.5462. Min Act: -0.0001

Data Index: 1359899 (Python Code)

Max Activating Token Index: 824