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

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

Neuron 3203 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: 1.5163. Min Range: -1.5163

Max Act: 1.5163. Min Act: -0.0000

Data Index: 1138542 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.1901. Min Act: -0.0000

Data Index: 109321 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.9894. Min Act: -0.0000

Data Index: 718291 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.8956. Min Act: -0.0000

Data Index: 1033370 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.8673. Min Act: -0.0000

Data Index: 372258 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.8022. Min Act: -0.0000

Data Index: 1074582 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.8062. Min Act: -0.0000

Data Index: 133580 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.8724. Min Act: -0.0000

Data Index: 1133305 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.8165. Min Act: -0.0000

Data Index: 660944 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.7735. Min Act: -0.0000

Data Index: 1241673 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.7652. Min Act: -0.0001

Data Index: 536048 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.7580. Min Act: -0.0000

Data Index: 797824 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.7417. Min Act: -0.0000

Data Index: 577860 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.7335. Min Act: -0.0000

Data Index: 282523 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.7210. Min Act: -0.0000

Data Index: 885175 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.7323. Min Act: -0.0000

Data Index: 1282897 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.6546. Min Act: -0.0000

Data Index: 331754 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.8105. Min Act: -0.0000

Data Index: 337561 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.7739. Min Act: -0.0000

Data Index: 450565 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.6349. Min Act: -0.0000

Data Index: 6863 (C4 (Web Text))

Max Activating Token Index: 214