Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4760 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0059. Min Range: -2.0059

Max Act: 2.0059. Min Act: -0.0000

Data Index: 1585310 (Python Code)

Max Activating Token Index: 429

Text #1

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.4848. Min Act: -0.0000

Data Index: 1440792 (Python Code)

Max Activating Token Index: 145

Text #2

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.4422. Min Act: -0.0000

Data Index: 1401745 (Python Code)

Max Activating Token Index: 478

Text #3

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.3236. Min Act: -0.0000

Data Index: 1520325 (Python Code)

Max Activating Token Index: 161

Text #4

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.3774. Min Act: -0.0000

Data Index: 1435981 (Python Code)

Max Activating Token Index: 281

Text #5

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.3549. Min Act: -0.0000

Data Index: 1377664 (Python Code)

Max Activating Token Index: 211

Text #6

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.2770. Min Act: -0.0000

Data Index: 1599688 (Python Code)

Max Activating Token Index: 55

Text #7

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.3230. Min Act: -0.0000

Data Index: 1537941 (Python Code)

Max Activating Token Index: 239

Text #8

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.2748. Min Act: -0.0000

Data Index: 1557536 (Python Code)

Max Activating Token Index: 39

Text #9

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.2155. Min Act: -0.0000

Data Index: 1575013 (Python Code)

Max Activating Token Index: 270

Text #10

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.1285. Min Act: 0.0000

Data Index: 1000483 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.2135. Min Act: -0.0000

Data Index: 1448383 (Python Code)

Max Activating Token Index: 797

Text #12

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.0962. Min Act: -0.0000

Data Index: 1608627 (Python Code)

Max Activating Token Index: 463

Text #13

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.0871. Min Act: -0.0000

Data Index: 1381934 (Python Code)

Max Activating Token Index: 286

Text #14

Max Range: 2.0059. Min Range: -2.0059

Max Act: 0.9899. Min Act: -0.0000

Data Index: 745033 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 2.0059. Min Range: -2.0059

Max Act: 1.0929. Min Act: -0.0000

Data Index: 1361193 (Python Code)

Max Activating Token Index: 674

Text #16

Max Range: 2.0059. Min Range: -2.0059

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1590844 (Python Code)

Max Activating Token Index: 399

Text #17

Max Range: 2.0059. Min Range: -2.0059

Max Act: 0.9143. Min Act: -0.0000

Data Index: 1626508 (Python Code)

Max Activating Token Index: 211

Text #18

Max Range: 2.0059. Min Range: -2.0059

Max Act: 0.8873. Min Act: -0.0000

Data Index: 1370703 (Python Code)

Max Activating Token Index: 380

Text #19

Max Range: 2.0059. Min Range: -2.0059

Max Act: 0.8856. Min Act: -0.0000

Data Index: 1382030 (Python Code)

Max Activating Token Index: 625