Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1522 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 4.6190. Min Range: -4.6190

Max Act: 4.6190. Min Act: -0.0002

Data Index: 1404614 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 4.6190. Min Range: -4.6190

Max Act: 3.6370. Min Act: -0.0002

Data Index: 1612379 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 4.6190. Min Range: -4.6190

Max Act: 3.7357. Min Act: -0.0002

Data Index: 1541309 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 4.6190. Min Range: -4.6190

Max Act: 2.4334. Min Act: -0.0002

Data Index: 1615038 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 4.6190. Min Range: -4.6190

Max Act: 2.7624. Min Act: -0.0002

Data Index: 1546279 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 4.6190. Min Range: -4.6190

Max Act: 2.7862. Min Act: -0.0002

Data Index: 1452589 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 4.6190. Min Range: -4.6190

Max Act: 2.2191. Min Act: -0.0002

Data Index: 1563020 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 4.6190. Min Range: -4.6190

Max Act: 2.3481. Min Act: -0.0002

Data Index: 1619087 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 4.6190. Min Range: -4.6190

Max Act: 2.4321. Min Act: -0.0002

Data Index: 1653386 (Python Code)

Max Activating Token Index: 8

Text #9

Max Range: 4.6190. Min Range: -4.6190

Max Act: 2.2659. Min Act: -0.0002

Data Index: 1522395 (Python Code)

Max Activating Token Index: 7

Text #10

Max Range: 4.6190. Min Range: -4.6190

Max Act: 2.1233. Min Act: -0.0002

Data Index: 1557991 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 4.6190. Min Range: -4.6190

Max Act: 2.1508. Min Act: -0.0002

Data Index: 1369579 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 4.6190. Min Range: -4.6190

Max Act: 2.1805. Min Act: -0.0002

Data Index: 1551773 (Python Code)

Max Activating Token Index: 4

Text #13

Max Range: 4.6190. Min Range: -4.6190

Max Act: 2.1042. Min Act: -0.0002

Data Index: 1393097 (Python Code)

Max Activating Token Index: 6

Text #14

Max Range: 4.6190. Min Range: -4.6190

Max Act: 2.1668. Min Act: -0.0002

Data Index: 1591320 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 4.6190. Min Range: -4.6190

Max Act: 2.1109. Min Act: -0.0002

Data Index: 1524701 (Python Code)

Max Activating Token Index: 3

Text #16

Max Range: 4.6190. Min Range: -4.6190

Max Act: 2.2334. Min Act: -0.0002

Data Index: 1544005 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 4.6190. Min Range: -4.6190

Max Act: 1.9961. Min Act: -0.0002

Data Index: 1522133 (Python Code)

Max Activating Token Index: 6

Text #18

Max Range: 4.6190. Min Range: -4.6190

Max Act: 2.0277. Min Act: -0.0002

Data Index: 1598211 (Python Code)

Max Activating Token Index: 4

Text #19

Max Range: 4.6190. Min Range: -4.6190

Max Act: 2.0172. Min Act: -0.0002

Data Index: 1631780 (Python Code)

Max Activating Token Index: 3