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

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

Neuron 3477 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: 0.9187. Min Range: -0.9187

Max Act: 0.9187. Min Act: -0.0001

Data Index: 1466800 (Python Code)

Max Activating Token Index: 255

Text #1

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.8207. Min Act: -0.0000

Data Index: 1361009 (Python Code)

Max Activating Token Index: 30

Text #2

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.8407. Min Act: -0.0001

Data Index: 1565187 (Python Code)

Max Activating Token Index: 282

Text #3

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.8068. Min Act: -0.0001

Data Index: 1520960 (Python Code)

Max Activating Token Index: 58

Text #4

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7600. Min Act: -0.0000

Data Index: 1645477 (Python Code)

Max Activating Token Index: 142

Text #5

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.6912. Min Act: -0.0001

Data Index: 1445170 (Python Code)

Max Activating Token Index: 197

Text #6

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7600. Min Act: -0.0001

Data Index: 1549553 (Python Code)

Max Activating Token Index: 213

Text #7

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7783. Min Act: -0.0001

Data Index: 1550345 (Python Code)

Max Activating Token Index: 811

Text #8

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7593. Min Act: -0.0001

Data Index: 1383809 (Python Code)

Max Activating Token Index: 977

Text #9

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7572. Min Act: -0.0000

Data Index: 1383478 (Python Code)

Max Activating Token Index: 455

Text #10

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7607. Min Act: -0.0001

Data Index: 1541743 (Python Code)

Max Activating Token Index: 44

Text #11

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7590. Min Act: -0.0001

Data Index: 1614624 (Python Code)

Max Activating Token Index: 637

Text #12

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7261. Min Act: -0.0001

Data Index: 1504290 (Python Code)

Max Activating Token Index: 117

Text #13

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7431. Min Act: -0.0001

Data Index: 1474181 (Python Code)

Max Activating Token Index: 566

Text #14

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7408. Min Act: -0.0000

Data Index: 1469982 (Python Code)

Max Activating Token Index: 122

Text #15

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7153. Min Act: -0.0001

Data Index: 1456975 (Python Code)

Max Activating Token Index: 535

Text #16

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.6063. Min Act: -0.0001

Data Index: 1580261 (Python Code)

Max Activating Token Index: 222

Text #17

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.7031. Min Act: -0.0001

Data Index: 1456018 (Python Code)

Max Activating Token Index: 272

Text #18

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.6380. Min Act: -0.0001

Data Index: 1517742 (Python Code)

Max Activating Token Index: 251

Text #19

Max Range: 0.9187. Min Range: -0.9187

Max Act: 0.6104. Min Act: -0.0001

Data Index: 1531290 (Python Code)

Max Activating Token Index: 229