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

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

Neuron 3444 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: 3.0019. Min Range: -3.0019

Max Act: 3.0019. Min Act: -0.0001

Data Index: 1435960 (Python Code)

Max Activating Token Index: 415

Text #1

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.6125. Min Act: -0.0001

Data Index: 1614421 (Python Code)

Max Activating Token Index: 308

Text #2

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.1144. Min Act: -0.0001

Data Index: 1529046 (Python Code)

Max Activating Token Index: 230

Text #3

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.3350. Min Act: -0.0001

Data Index: 1592747 (Python Code)

Max Activating Token Index: 324

Text #4

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.3235. Min Act: -0.0001

Data Index: 1482987 (Python Code)

Max Activating Token Index: 907

Text #5

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.1908. Min Act: -0.0001

Data Index: 1540592 (Python Code)

Max Activating Token Index: 951

Text #6

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.2718. Min Act: -0.0001

Data Index: 1414433 (Python Code)

Max Activating Token Index: 30

Text #7

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.2423. Min Act: -0.0001

Data Index: 1461943 (Python Code)

Max Activating Token Index: 123

Text #8

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.3595. Min Act: -0.0001

Data Index: 1436822 (Python Code)

Max Activating Token Index: 261

Text #9

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.2262. Min Act: -0.0001

Data Index: 1539743 (Python Code)

Max Activating Token Index: 150

Text #10

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.3560. Min Act: -0.0001

Data Index: 1641032 (Python Code)

Max Activating Token Index: 874

Text #11

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.0789. Min Act: -0.0001

Data Index: 1566058 (Python Code)

Max Activating Token Index: 150

Text #12

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.0822. Min Act: -0.0001

Data Index: 1492265 (Python Code)

Max Activating Token Index: 946

Text #13

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.0720. Min Act: -0.0001

Data Index: 1656873 (Python Code)

Max Activating Token Index: 916

Text #14

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.0511. Min Act: -0.0001

Data Index: 1547664 (Python Code)

Max Activating Token Index: 237

Text #15

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.0603. Min Act: -0.0001

Data Index: 1644841 (Python Code)

Max Activating Token Index: 126

Text #16

Max Range: 3.0019. Min Range: -3.0019

Max Act: 1.8130. Min Act: -0.0001

Data Index: 1655768 (Python Code)

Max Activating Token Index: 325

Text #17

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.0462. Min Act: -0.0001

Data Index: 1506231 (Python Code)

Max Activating Token Index: 315

Text #18

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.2411. Min Act: -0.0001

Data Index: 1527200 (Python Code)

Max Activating Token Index: 169

Text #19

Max Range: 3.0019. Min Range: -3.0019

Max Act: 2.1204. Min Act: -0.0001

Data Index: 1655274 (Python Code)

Max Activating Token Index: 99