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

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

Neuron 1075 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1880. Min Act: -0.0005

Data Index: 627644 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1738. Min Act: -0.0005

Data Index: 111360 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1670. Min Act: -0.0005

Data Index: 918056 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1597. Min Act: -0.0005

Data Index: 390208 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1524. Min Act: -0.0005

Data Index: 919983 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1558. Min Act: -0.0005

Data Index: 77038 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1538. Min Act: -0.0005

Data Index: 375987 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1423. Min Act: -0.0005

Data Index: 692616 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1528. Min Act: -0.0005

Data Index: 399221 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1416. Min Act: -0.0005

Data Index: 1293214 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1417. Min Act: -0.0005

Data Index: 1170195 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1456. Min Act: -0.0005

Data Index: 884131 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1441. Min Act: -0.0005

Data Index: 92716 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1446. Min Act: -0.0005

Data Index: 1097748 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1367. Min Act: -0.0005

Data Index: 962286 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1418. Min Act: -0.0005

Data Index: 114149 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1467. Min Act: -0.0005

Data Index: 629011 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1467. Min Act: -0.0005

Data Index: 446166 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1408. Min Act: -0.0005

Data Index: 1324902 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1357. Min Act: -0.0005

Data Index: 1075666 (C4 (Web Text))

Max Activating Token Index: 158