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

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

Neuron 2544 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4603. Min Act: -0.0001

Data Index: 1518705 (Python Code)

Max Activating Token Index: 232

Text #1

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1419402 (Python Code)

Max Activating Token Index: 540

Text #2

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4027. Min Act: -0.0001

Data Index: 1367423 (Python Code)

Max Activating Token Index: 207

Text #3

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3905. Min Act: -0.0000

Data Index: 1383889 (Python Code)

Max Activating Token Index: 723

Text #4

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3031. Min Act: -0.0000

Data Index: 1505044 (Python Code)

Max Activating Token Index: 711

Text #5

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.2881. Min Act: -0.0001

Data Index: 1572875 (Python Code)

Max Activating Token Index: 239

Text #6

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3065. Min Act: -0.0000

Data Index: 1620285 (Python Code)

Max Activating Token Index: 21

Text #7

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.2787. Min Act: -0.0000

Data Index: 1366935 (Python Code)

Max Activating Token Index: 586

Text #8

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1649013 (Python Code)

Max Activating Token Index: 838

Text #9

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.2489. Min Act: -0.0000

Data Index: 1538281 (Python Code)

Max Activating Token Index: 676

Text #10

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.2495. Min Act: -0.0001

Data Index: 1447237 (Python Code)

Max Activating Token Index: 145

Text #11

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.2242. Min Act: -0.0000

Data Index: 1481190 (Python Code)

Max Activating Token Index: 23

Text #12

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.2219. Min Act: -0.0000

Data Index: 1487137 (Python Code)

Max Activating Token Index: 578

Text #13

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1560674 (Python Code)

Max Activating Token Index: 597

Text #14

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.2203. Min Act: -0.0000

Data Index: 1425032 (Python Code)

Max Activating Token Index: 592

Text #15

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.2230. Min Act: -0.0000

Data Index: 1376604 (Python Code)

Max Activating Token Index: 342

Text #16

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.2217. Min Act: -0.0000

Data Index: 1580812 (Python Code)

Max Activating Token Index: 1022

Text #17

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.2065. Min Act: -0.0001

Data Index: 1398007 (Python Code)

Max Activating Token Index: 434

Text #18

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.2047. Min Act: -0.0001

Data Index: 1563970 (Python Code)

Max Activating Token Index: 68

Text #19

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.2187. Min Act: -0.0000

Data Index: 1491172 (Python Code)

Max Activating Token Index: 810