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

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

Neuron 3945 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: 1.4020. Min Range: -1.4020

Max Act: 1.4020. Min Act: -0.0000

Data Index: 1388995 (Python Code)

Max Activating Token Index: 493

Text #1

Max Range: 1.4020. Min Range: -1.4020

Max Act: 1.3332. Min Act: -0.0000

Data Index: 1363180 (Python Code)

Max Activating Token Index: 428

Text #2

Max Range: 1.4020. Min Range: -1.4020

Max Act: 1.3149. Min Act: -0.0001

Data Index: 1453001 (Python Code)

Max Activating Token Index: 14

Text #3

Max Range: 1.4020. Min Range: -1.4020

Max Act: 1.2214. Min Act: -0.0001

Data Index: 1634265 (Python Code)

Max Activating Token Index: 243

Text #4

Max Range: 1.4020. Min Range: -1.4020

Max Act: 1.2556. Min Act: -0.0001

Data Index: 91783 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 1.4020. Min Range: -1.4020

Max Act: 1.1701. Min Act: -0.0000

Data Index: 1486800 (Python Code)

Max Activating Token Index: 58

Text #6

Max Range: 1.4020. Min Range: -1.4020

Max Act: 1.1286. Min Act: -0.0000

Data Index: 1605990 (Python Code)

Max Activating Token Index: 842

Text #7

Max Range: 1.4020. Min Range: -1.4020

Max Act: 1.0329. Min Act: -0.0001

Data Index: 1445487 (Python Code)

Max Activating Token Index: 656

Text #8

Max Range: 1.4020. Min Range: -1.4020

Max Act: 1.1319. Min Act: -0.0000

Data Index: 1438531 (Python Code)

Max Activating Token Index: 190

Text #9

Max Range: 1.4020. Min Range: -1.4020

Max Act: 1.0386. Min Act: -0.0001

Data Index: 1646302 (Python Code)

Max Activating Token Index: 100

Text #10

Max Range: 1.4020. Min Range: -1.4020

Max Act: 1.0629. Min Act: -0.0000

Data Index: 1465101 (Python Code)

Max Activating Token Index: 898

Text #11

Max Range: 1.4020. Min Range: -1.4020

Max Act: 1.1563. Min Act: -0.0001

Data Index: 1539291 (Python Code)

Max Activating Token Index: 162

Text #12

Max Range: 1.4020. Min Range: -1.4020

Max Act: 1.0721. Min Act: -0.0000

Data Index: 1534915 (Python Code)

Max Activating Token Index: 820

Text #13

Max Range: 1.4020. Min Range: -1.4020

Max Act: 1.0103. Min Act: -0.0001

Data Index: 1616707 (Python Code)

Max Activating Token Index: 363

Text #14

Max Range: 1.4020. Min Range: -1.4020

Max Act: 1.0401. Min Act: -0.0000

Data Index: 1621009 (Python Code)

Max Activating Token Index: 347

Text #15

Max Range: 1.4020. Min Range: -1.4020

Max Act: 1.0234. Min Act: -0.0000

Data Index: 1644458 (Python Code)

Max Activating Token Index: 824

Text #16

Max Range: 1.4020. Min Range: -1.4020

Max Act: 0.9627. Min Act: -0.0000

Data Index: 1574575 (Python Code)

Max Activating Token Index: 599

Text #17

Max Range: 1.4020. Min Range: -1.4020

Max Act: 1.0825. Min Act: -0.0001

Data Index: 1509956 (Python Code)

Max Activating Token Index: 843

Text #18

Max Range: 1.4020. Min Range: -1.4020

Max Act: 1.0132. Min Act: -0.0000

Data Index: 1591595 (Python Code)

Max Activating Token Index: 475

Text #19

Max Range: 1.4020. Min Range: -1.4020

Max Act: 0.9354. Min Act: -0.0000

Data Index: 1448615 (Python Code)

Max Activating Token Index: 604