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

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

Neuron 4873 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.6483. Min Act: -0.0000

Data Index: 1378239 (Python Code)

Max Activating Token Index: 330

Text #1

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.6239. Min Act: -0.0000

Data Index: 1387955 (Python Code)

Max Activating Token Index: 318

Text #2

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.6368. Min Act: -0.0000

Data Index: 1607949 (Python Code)

Max Activating Token Index: 511

Text #3

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.6285. Min Act: -0.0000

Data Index: 1434172 (Python Code)

Max Activating Token Index: 42

Text #4

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.6364. Min Act: -0.0000

Data Index: 1557287 (Python Code)

Max Activating Token Index: 118

Text #5

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.5775. Min Act: -0.0000

Data Index: 1486802 (Python Code)

Max Activating Token Index: 25

Text #6

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.5142. Min Act: -0.0000

Data Index: 1580961 (Python Code)

Max Activating Token Index: 532

Text #7

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.5360. Min Act: -0.0000

Data Index: 1635706 (Python Code)

Max Activating Token Index: 514

Text #8

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.5331. Min Act: -0.0000

Data Index: 1510722 (Python Code)

Max Activating Token Index: 105

Text #9

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.4858. Min Act: -0.0000

Data Index: 1613023 (Python Code)

Max Activating Token Index: 600

Text #10

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.5119. Min Act: -0.0000

Data Index: 1455661 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.3620. Min Act: -0.0000

Data Index: 1606728 (Python Code)

Max Activating Token Index: 128

Text #12

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.4874. Min Act: -0.0000

Data Index: 1470575 (Python Code)

Max Activating Token Index: 427

Text #13

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.3903. Min Act: -0.0000

Data Index: 1648881 (Python Code)

Max Activating Token Index: 269

Text #14

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.4234. Min Act: -0.0000

Data Index: 1401346 (Python Code)

Max Activating Token Index: 43

Text #15

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.4181. Min Act: -0.0000

Data Index: 1505649 (Python Code)

Max Activating Token Index: 843

Text #16

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.4543. Min Act: -0.0000

Data Index: 1492359 (Python Code)

Max Activating Token Index: 545

Text #17

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.3154. Min Act: -0.0000

Data Index: 1362553 (Python Code)

Max Activating Token Index: 247

Text #18

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.3865. Min Act: -0.0000

Data Index: 1600740 (Python Code)

Max Activating Token Index: 600

Text #19

Max Range: 1.6483. Min Range: -1.6483

Max Act: 1.3833. Min Act: -0.0000

Data Index: 1607024 (Python Code)

Max Activating Token Index: 227