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

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

Neuron 2902 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.9051. Min Act: 0.0001

Data Index: 1464960 (Python Code)

Max Activating Token Index: 113

Text #1

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1399821 (Python Code)

Max Activating Token Index: 811

Text #2

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.8368. Min Act: 0.0000

Data Index: 1411427 (Python Code)

Max Activating Token Index: 757

Text #3

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1397209 (Python Code)

Max Activating Token Index: 511

Text #4

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7848. Min Act: -0.0000

Data Index: 1441947 (Python Code)

Max Activating Token Index: 169

Text #5

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.8069. Min Act: -0.0000

Data Index: 1528371 (Python Code)

Max Activating Token Index: 680

Text #6

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7398. Min Act: -0.0000

Data Index: 309090 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7317. Min Act: 0.0002

Data Index: 1396593 (Python Code)

Max Activating Token Index: 225

Text #8

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7691. Min Act: -0.0000

Data Index: 1445010 (Python Code)

Max Activating Token Index: 43

Text #9

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7505. Min Act: 0.0002

Data Index: 1429729 (Python Code)

Max Activating Token Index: 384

Text #10

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7268. Min Act: -0.0000

Data Index: 1517376 (Python Code)

Max Activating Token Index: 206

Text #11

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7169. Min Act: 0.0000

Data Index: 49924 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.6861. Min Act: -0.0000

Data Index: 1368647 (Python Code)

Max Activating Token Index: 321

Text #13

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7068. Min Act: 0.0001

Data Index: 1636697 (Python Code)

Max Activating Token Index: 105

Text #14

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7043. Min Act: -0.0000

Data Index: 35434 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7046. Min Act: -0.0000

Data Index: 1507790 (Python Code)

Max Activating Token Index: 839

Text #16

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.6483. Min Act: 0.0000

Data Index: 1504363 (Python Code)

Max Activating Token Index: 650

Text #17

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7222. Min Act: 0.0000

Data Index: 1630247 (Python Code)

Max Activating Token Index: 635

Text #18

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.7204. Min Act: 0.0000

Data Index: 1578757 (Python Code)

Max Activating Token Index: 292

Text #19

Max Range: 0.9051. Min Range: -0.9051

Max Act: 0.6722. Min Act: 0.0001

Data Index: 1442731 (Python Code)

Max Activating Token Index: 162