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

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

Neuron 654 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: 1.2367. Min Range: -1.2367

Max Act: 1.2367. Min Act: -0.0001

Data Index: 1509705 (Python Code)

Max Activating Token Index: 11

Text #1

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.1703. Min Act: -0.0001

Data Index: 1459951 (Python Code)

Max Activating Token Index: 1016

Text #2

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.1942. Min Act: -0.0001

Data Index: 1565417 (Python Code)

Max Activating Token Index: 1019

Text #3

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.0921. Min Act: -0.0001

Data Index: 1400029 (Python Code)

Max Activating Token Index: 1020

Text #4

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.1126. Min Act: -0.0001

Data Index: 1573789 (Python Code)

Max Activating Token Index: 1008

Text #5

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.1340. Min Act: -0.0001

Data Index: 1643105 (Python Code)

Max Activating Token Index: 1016

Text #6

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.1032. Min Act: -0.0001

Data Index: 1616462 (Python Code)

Max Activating Token Index: 1006

Text #7

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.1239. Min Act: -0.0001

Data Index: 1486218 (Python Code)

Max Activating Token Index: 1019

Text #8

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.1282. Min Act: -0.0001

Data Index: 1369061 (Python Code)

Max Activating Token Index: 15

Text #9

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.1297. Min Act: -0.0001

Data Index: 1551620 (Python Code)

Max Activating Token Index: 1016

Text #10

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.1487. Min Act: -0.0001

Data Index: 1372486 (Python Code)

Max Activating Token Index: 997

Text #11

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.1188. Min Act: -0.0001

Data Index: 1454484 (Python Code)

Max Activating Token Index: 995

Text #12

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.1158. Min Act: -0.0001

Data Index: 1604675 (Python Code)

Max Activating Token Index: 1009

Text #13

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.0901. Min Act: -0.0001

Data Index: 1547312 (Python Code)

Max Activating Token Index: 1021

Text #14

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.1049. Min Act: -0.0001

Data Index: 1372356 (Python Code)

Max Activating Token Index: 1020

Text #15

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.1162. Min Act: -0.0001

Data Index: 1635601 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.0441. Min Act: -0.0001

Data Index: 1395740 (Python Code)

Max Activating Token Index: 1020

Text #17

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.1456. Min Act: -0.0001

Data Index: 1631357 (Python Code)

Max Activating Token Index: 1004

Text #18

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.0732. Min Act: -0.0001

Data Index: 1550620 (Python Code)

Max Activating Token Index: 1001

Text #19

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.1071. Min Act: -0.0001

Data Index: 1592486 (Python Code)

Max Activating Token Index: 965