Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1893 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.5348. Min Act: -0.0000

Data Index: 1462200 (Python Code)

Max Activating Token Index: 44

Text #1

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.5267. Min Act: -0.0000

Data Index: 1378081 (Python Code)

Max Activating Token Index: 1008

Text #2

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.2867. Min Act: -0.0000

Data Index: 1629111 (Python Code)

Max Activating Token Index: 776

Text #3

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.4685. Min Act: -0.0000

Data Index: 1433200 (Python Code)

Max Activating Token Index: 694

Text #4

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.1063. Min Act: -0.0000

Data Index: 1515857 (Python Code)

Max Activating Token Index: 876

Text #5

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.3459. Min Act: -0.0000

Data Index: 1608093 (Python Code)

Max Activating Token Index: 576

Text #6

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.3454. Min Act: -0.0000

Data Index: 1567197 (Python Code)

Max Activating Token Index: 741

Text #7

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.1695. Min Act: -0.0000

Data Index: 1462158 (Python Code)

Max Activating Token Index: 168

Text #8

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.3055. Min Act: -0.0001

Data Index: 1460769 (Python Code)

Max Activating Token Index: 32

Text #9

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.1867. Min Act: -0.0000

Data Index: 1450834 (Python Code)

Max Activating Token Index: 24

Text #10

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.2191. Min Act: -0.0000

Data Index: 1616879 (Python Code)

Max Activating Token Index: 73

Text #11

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.1406. Min Act: -0.0000

Data Index: 1437713 (Python Code)

Max Activating Token Index: 72

Text #12

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.2332. Min Act: -0.0000

Data Index: 1402110 (Python Code)

Max Activating Token Index: 939

Text #13

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.0487. Min Act: -0.0000

Data Index: 1535288 (Python Code)

Max Activating Token Index: 789

Text #14

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.1226. Min Act: -0.0000

Data Index: 1510983 (Python Code)

Max Activating Token Index: 611

Text #15

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.1917. Min Act: -0.0000

Data Index: 1561349 (Python Code)

Max Activating Token Index: 22

Text #16

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.1208. Min Act: -0.0000

Data Index: 1529937 (Python Code)

Max Activating Token Index: 44

Text #17

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.2170. Min Act: -0.0000

Data Index: 1479696 (Python Code)

Max Activating Token Index: 558

Text #18

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.1488. Min Act: -0.0001

Data Index: 1619981 (Python Code)

Max Activating Token Index: 44

Text #19

Max Range: 1.5348. Min Range: -1.5348

Max Act: 1.0712. Min Act: -0.0001

Data Index: 1621920 (Python Code)

Max Activating Token Index: 13